© 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. 151903
    Prev
    Next
    INDEX
    Explanations

    discussion about

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

    conversation starters and flow

    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
    ma
    0.55
    ：
    0.54
     वेगवेगळ्या
    0.52
     eril
    0.52
     pust
    0.52
    如下图
    0.52
    ek
    0.50
    är
    0.50
     conflicting
    0.50
     inconsistencies
    0.49
    POSITIVE LOGITS
    يد
    0.76
    ה
    0.76
    ка
    0.70
     discusión
    0.69
    ه
    0.69
    ва
    0.68
    ви
    0.66
    бы
    0.66
    약
    0.66
    ﾛ
    0.64
    Activations Density 0.036%

    No Known Activations