© 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. 20162
    Prev
    Next
    INDEX
    Explanations

    all of these

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

    specific general skills you

    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
    ’
    0.53
    on
    0.52
    だったので
    0.50
    '
    0.49
    ada
    0.48
    洒落
    0.47
    to
    0.46
    allow
    0.46
     avait
    0.44
     O
    0.44
    POSITIVE LOGITS
    Feign
    0.52
     ಯಾವಾಗ
    0.50
     باتیں
    0.49
     نفسك
    0.47
     बातें
    0.46
     perguntas
    0.46
     기본적인
    0.45
     quieres
    0.45
     संज्ञा
    0.45
     inversely
    0.44
    Activations Density 0.000%

    No Known Activations