© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 135823
    Prev
    Next
    INDEX
    Explanations

    keywords followed by specific continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     của
    0.50
    ято
    0.48
    yı
    0.47
     เหรอ
    0.47
     của
    0.46
    ē
    0.46
     by
    0.45
     niya
    0.44
    mot
    0.44
    okay
    0.44
    POSITIVE LOGITS
     нередко
    0.52
    貥
    0.46
    付近
    0.45
     \%
    0.43
    ysseus
    0.43
    ⿷
    0.43
    Persistent
    0.42
     типу
    0.42
    QUID
    0.42
    ologica
    0.41
    Activations Density 0.001%

    No Known Activations