© 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. 6392
    Prev
    Next
    INDEX
    Explanations

    import/native/std/View

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

    programming language imports and keywords

    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
     सूख
    0.36
     শ্বাস
    0.35
    OLYBD
    0.34
    রোগ
    0.34
    spacePad
    0.33
    শিষ্ট
    0.32
    嫘
    0.32
    OLYBDENUM
    0.32
    VSLU
    0.32
     kanamycin
    0.32
    POSITIVE LOGITS
    -
    0.43
    、
    0.37
    _
    0.35
    ,
    0.35
     -
    0.35
    *
    0.35
    u
    0.34
     –
    0.33
    /
    0.33
    &
    0.32
    Activations Density 0.000%

    No Known Activations