© 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. 17600
    Prev
    Next
    INDEX
    Explanations

    Ron Paul, frost early, invoice must

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

    Holocaust, Pleasure, illegal, cloning, CSS

    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
    גל
    0.48
    颓
    0.46
     ait
    0.46
    ס
    0.44
    ไ
    0.44
    डाउन
    0.43
    Glo
    0.43
    或者
    0.43
    หว่าง
    0.43
    ส
    0.43
    POSITIVE LOGITS
     पुअनि
    0.46
     Evidently
    0.43
    ekkür
    0.42
     disrupts
    0.41
     discontinuities
    0.40
     intermitt
    0.39
     Serialization
    0.39
     Involvement
    0.38
    ırmaya
    0.38
     disruptions
    0.38
    Activations Density 0.000%

    No Known Activations