© 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. 186314
    Prev
    Next
    INDEX
    Explanations

    upcoming family vacation

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

    watching every, text box, rigid, cycle lanes, impacting vegetable, value

    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
    အတွ
    0.55
     мин
    0.54
     さらに
    0.54
     IONS
    0.54
     PROGRAM
    0.52
     STREAM
    0.52
    ﾖ
    0.52
     INDUST
    0.51
    CLUSTERED
    0.51
     取っ
    0.51
    POSITIVE LOGITS
    ा
    0.47
     vanilla
    0.47
    Sub
    0.46
     tolerance
    0.46
     fantasy
    0.45
     fantasia
    0.45
     rebellion
    0.44
     sledge
    0.44
     be
    0.44
    -
    0.44
    Activations Density 0.001%

    No Known Activations