© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6401
    Prev
    Next
    INDEX
    Explanations

    conclusion is

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects present-tense linking or stative constructions (especially “is”/“are” and similar verbs) that assert or describe a quality.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     idk
    1.18
    😕
    1.13
     powodu
    1.05
     unsatisfactory
    1.05
     некоторых
    1.04
     некоторые
    1.02
     някои
    1.02
    𒐪
    1.02
    😑
    1.00
     sommige
    1.00
    POSITIVE LOGITS
     deftly
    1.09
     आत्मविश्वास
    0.94
    はもちろん
    0.93
     brimming
    0.93
     effortlessly
    0.91
     impecc
    0.90
     expertly
    0.89
     masterful
    0.88
    ならでは
    0.88
    すべて
    0.87
    Activations Density 0.948%

    No Known Activations