© 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. 34827
    Prev
    Next
    INDEX
    Explanations

    manuals and diagrams

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

    seek to build relationships

    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
    1
    0.59
    م
    0.54
    mö
    0.49
     quilting
    0.48
     る
    0.47
     ry
    0.47
     backlight
    0.44
     Typed
    0.44
     pedestal
    0.44
    ্মদ
    0.43
    POSITIVE LOGITS
     protons
    0.41
     understandings
    0.40
    🍏
    0.40
    createText
    0.39
    უნქ
    0.38
    }^{-},
    0.38
    ahrenheit
    0.38
    rents
    0.38
    currentToken
    0.38
     ದಾಖ
    0.38
    Activations Density 0.000%

    No Known Activations