© 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. 145058
    Prev
    Next
    INDEX
    Explanations

    mobile app or toilets

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

    Convert to CSV

    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
    \
    0.59
    retching
    0.52
     Sobolev
    0.50
    )'
    0.45
    වි
    0.44
    {$\
    0.43
     airlines
    0.42
    \\\
    0.42
     修改
    0.41
    ℝ
    0.41
    POSITIVE LOGITS
    ünk
    0.46
    өлү
    0.45
    ার্থ
    0.45
    ającym
    0.44
    gruppe
    0.44
     nix
    0.44
     základ
    0.44
     cadmium
    0.42
    δό
    0.42
     gericht
    0.41
    Activations Density 0.000%

    No Known Activations