© 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. 28206
    Prev
    Next
    INDEX
    Explanations

    posted at time

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

    organization, classification, or state descriptions

    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
    ر
    0.57
    cmd
    0.54
    naire
    0.50
     interst
    0.48
    ings
    0.48
    dec
    0.48
    br
    0.47
    numbers
    0.47
     cmd
    0.46
     खतरे
    0.46
    POSITIVE LOGITS
    कल्चर
    0.43
    সৌ
    0.43
    🍐
    0.42
     প্রভৃতি
    0.42
     lengthening
    0.41
    導演
    0.40
     preacher
    0.40
    ၣ်
    0.39
     installing
    0.39
    惱
    0.39
    Activations Density 0.000%

    No Known Activations