© 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. 23927
    Prev
    Next
    INDEX
    Explanations

    Automatic transmission

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

    accept, allow, from, regardless

    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
    Statements
    0.49
    neur
    0.47
    Lb
    0.46
     सोन
    0.45
     Stellung
    0.45
    }.
    0.45
     առաջ
    0.45
    endige
    0.44
    (
    0.44
    iejs
    0.44
    POSITIVE LOGITS
    스와
    0.59
    스가
    0.56
    스
    0.55
     espécie
    0.54
    스를
    0.53
    섣
    0.50
     with
    0.49
    스로
    0.48
     pedi
    0.47
    세를
    0.47
    Activations Density 0.001%

    No Known Activations