© 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. 101322
    Prev
    Next
    INDEX
    Explanations

    golden apples

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

    patterns, tone, registration

    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
    🥞
    0.48
     hôm
    0.48
     vrijdag
    0.47
     usia
    0.46
     pię
    0.45
     daleko
    0.45
    䂙
    0.45
     stej
    0.44
     ekonomi
    0.44
    \|=
    0.44
    POSITIVE LOGITS
     Do
    0.47
    ).
    0.46
     Supremo
    0.45
     Pon
    0.45
     Additional
    0.45
     Confederate
    0.44
    Manip
    0.44
     Якщо
    0.44
     actionable
    0.43
    可以让
    0.43
    Activations Density 0.000%

    No Known Activations