© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 202471
    Prev
    Next
    INDEX
    Explanations

    year's trend

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

    pushing or pulling objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     Cualquier
    0.51
    전
    0.49
    custList
    0.47
    واي
    0.46
    떤
    0.46
     any
    0.46
     februar
    0.46
     ফুলের
    0.46
     कुनै
    0.45
    뛰
    0.45
    POSITIVE LOGITS
    idine
    0.42
     Ache
    0.42
     PhD
    0.42
    yd
    0.41
    ﹒
    0.41
    .
    0.40
     indium
    0.40
     UK
    0.40
     association
    0.40
     macroscopic
    0.39
    Activations Density 0.001%

    No Known Activations