© 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. 39125
    Prev
    Next
    INDEX
    Explanations

    numbers and units

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

    css styles and ui elements

    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
     遅く
    0.33
     ½
    0.32
     幅
    0.31
     বেঁ
    0.31
     kissed
    0.31
     mãos
    0.30
     oreilles
    0.30
     pentes
    0.30
     EDTA
    0.30
    zięki
    0.29
    POSITIVE LOGITS
    ivation
    0.33
    <unused981>
    0.33
    ก
    0.33
     ક્
    0.32
    <unused995>
    0.32
    EXP
    0.32
    ớm
    0.32
    strstr
    0.32
    乸
    0.32
    <unused2114>
    0.32
    Activations Density 0.004%

    No Known Activations