© 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. 50004
    Prev
    Next
    INDEX
    Explanations

    spending timedoing choresunique propertiesdoing mold

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

    variable flat

    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
     あれ
    0.56
     oameni
    0.55
     hemispheres
    0.55
     pertemuan
    0.54
     ܡ
    0.54
     chlorophyll
    0.53
     buttonAnimation
    0.53
     inh
    0.52
     入っ
    0.52
     話
    0.52
    POSITIVE LOGITS
    ivo
    0.45
    glied
    0.45
    anta
    0.44
    ats
    0.44
    urgo
    0.43
    b
    0.43
    Altura
    0.43
    igl
    0.42
    म्बर
    0.42
    ب
    0.42
    Activations Density 0.000%

    No Known Activations