© 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. 31-GEMMASCOPE-2-RES-16K
    7. 13044
    Prev
    Next
    INDEX
    Explanations

    in- context

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

    This neuron detects hyphenated “in-X” compounds (e.g. in-depth, in-house).

    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_31_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
    aria
    0.63
    abulous
    0.59
    ualaikum
    0.57
    Receiver
    0.56
    ok
    0.56
     め
    0.56
    ARIA
    0.56
     표시
    0.56
     由
    0.55
    ...!
    0.54
    POSITIVE LOGITS
     vitro
    0.89
     silico
    0.80
     situ
    0.73
     sitter
    0.60
     vivo
    0.59
    vitro
    0.55
     armchair
    0.54
     door
    0.52
    どのような
    0.52
     extenso
    0.52
    Activations Density 0.098%

    No Known Activations