© 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. 46717
    Prev
    Next
    INDEX
    Explanations

    JSON message field

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

    api response message

    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
     Fam
    0.46
     tetapi
    0.46
     ancak
    0.41
     تاہم
    0.40
     namun
    0.40
     hasilnya
    0.40
     mingle
    0.39
    ऱ
    0.39
    悖
    0.39
     판매
    0.38
    POSITIVE LOGITS
    ிகா
    0.46
    from
    0.45
    "^
    0.45
    人が
    0.44
    arccos
    0.43
    Attached
    0.42
    attached
    0.42
     machined
    0.42
    ',"
    0.41
    から
    0.41
    Activations Density 0.000%

    No Known Activations