© 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. 150295
    Prev
    Next
    INDEX
    Explanations

    return or null

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

    return None or empty

    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
    Since
    0.43
    নকে
    0.41
    াদ
    0.41
    现象
    0.39
     fenomeni
    0.39
    ਸੀ
    0.39
    دیای
    0.39
    徇
    0.39
    läuft
    0.38
    样子
    0.38
    POSITIVE LOGITS
     flaky
    0.46
     hyaluronic
    0.45
     Sx
    0.44
     切り
    0.43
     inorganic
    0.42
     archaic
    0.42
     semicon
    0.41
     bandit
    0.41
     quas
    0.41
     unreal
    0.41
    Activations Density 0.000%

    No Known Activations