© 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. 127665
    Prev
    Next
    INDEX
    Explanations

    information pending

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

    god, ensure, alloy, score, contingent, representations

    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
    称
    0.44
     ugl
    0.43
    ghe
    0.40
    RADIATION
    0.40
    厚
    0.40
    ッケ
    0.40
     societ
    0.39
     nennt
    0.39
     frictions
    0.39
    rq
    0.39
    POSITIVE LOGITS
     Danube
    0.50
    лений
    0.49
     European
    0.47
     Marca
    0.46
    സ്ഥ
    0.46
    лены
    0.45
    ject
    0.44
    javax
    0.44
     Beech
    0.44
    링
    0.44
    Activations Density 0.000%

    No Known Activations