© 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. 138967
    Prev
    Next
    INDEX
    Explanations

    dating sites

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

    logical fallacies, Reduction Act, adjective modification

    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
     ต้อง
    0.44
    Kum
    0.41
     AppModule
    0.40
    <0xB9>
    0.40
    ાર
    0.40
     เจ้า
    0.40
    还好
    0.40
    胭
    0.39
    )}$
    0.39
    <0x0D>
    0.39
    POSITIVE LOGITS
     affiliates
    0.45
     arcane
    0.43
     suffrage
    0.43
     taxonom
    0.42
    ونَ
    0.42
     sprouts
    0.41
     effektiv
    0.40
     enacted
    0.40
     both
    0.40
     prong
    0.40
    Activations Density 0.000%

    No Known Activations