© 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. 41474
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

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

    foreign language words

    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
    sides
    0.52
    ished
    0.44
    ican
    0.44
    ua
    0.44
    '
    0.43
    ït
    0.42
    vspace
    0.42
    タンク
    0.42
    ível
    0.41
    tble
    0.41
    POSITIVE LOGITS
     mavi
    0.48
    রাদ
    0.47
    ༤
    0.46
     Pampl
    0.45
     سين
    0.45
     texto
    0.45
     estaban
    0.45
    খা
    0.44
    然而
    0.44
     قيمة
    0.44
    Activations Density 0.000%

    No Known Activations