© 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. 160000
    Prev
    Next
    INDEX
    Explanations

    quantifiable metrics

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

    strings, settings, family

    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
    st
    0.50
    s
    0.50
     sujets
    0.49
    let
    0.46
    src
    0.44
     nele
    0.43
     departe
    0.43
    drop
    0.42
    ct
    0.42
    깊
    0.42
    POSITIVE LOGITS
     ប្រ
    0.52
     Ար
    0.52
     तापमान
    0.51
     వ్యవస్థ
    0.50
     bạc
    0.49
     ដែល
    0.47
     ដោយ
    0.47
    ణ
    0.47
    ण्यासाठी
    0.46
    ائیں
    0.46
    Activations Density 0.000%

    No Known Activations