© 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. 52687
    Prev
    Next
    INDEX
    Explanations

    signed up

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

    focus on positive aspects

    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
    ラの
    0.51
     GaAs
    0.48
    ム
    0.47
    ۰
    0.45
    異なる
    0.44
    ரிக்கை
    0.44
     करण
    0.43
     BACH
    0.43
     Susanne
    0.42
     JUAN
    0.41
    POSITIVE LOGITS
     tys
    0.50
    按照
    0.47
    日
    0.45
     कोस
    0.45
     thổ
    0.43
    根据
    0.42
    사
    0.42
    ys
    0.42
    體
    0.41
     utils
    0.41
    Activations Density 0.000%

    No Known Activations