© 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. 13152
    Prev
    Next
    INDEX
    Explanations

    flexibility vs rigidity

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

    The neuron responds to words describing a physical state of firmness or looseness (e.g. rigid, loose, floating, tighten, strict).

    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
     ervaring
    0.70
    世纪
    0.69
     daher
    0.67
    forKey
    0.67
    ریب
    0.65
     Jahrhunderts
    0.65
     yoğun
    0.64
    障
    0.64
    浓
    0.64
     подробно
    0.64
    POSITIVE LOGITS
     ríg
    1.08
     estrict
    1.02
     rigidly
    1.00
     rigidity
    0.98
     STRICT
    0.98
     strict
    0.96
     strictly
    0.94
     rigid
    0.92
     Rigid
    0.90
     rigor
    0.89
    Activations Density 0.136%

    No Known Activations