© 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. 203067
    Prev
    Next
    INDEX
    Explanations

    accompanied by

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

    state, condition, future

    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
     품질
    0.52
     만들기
    0.52
     기능
    0.49
     mumbled
    0.49
     ۽
    0.48
    ilerden
    0.47
     rendre
    0.47
    使う
    0.46
     움
    0.46
     punctuation
    0.46
    POSITIVE LOGITS
     Reef
    0.52
    ifert
    0.46
    foe
    0.45
     Ric
    0.44
     Carpet
    0.44
    اعه
    0.44
     Floors
    0.43
    ্ধ্য
    0.43
    Int
    0.42
    fold
    0.42
    Activations Density 0.000%

    No Known Activations