© 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. 35602
    Prev
    Next
    INDEX
    Explanations

    my boy, cleaning, listings

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

    useMemo, useReducer, structure

    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
     przetwarz
    0.46
     পরামর্শ
    0.43
     രാ
    0.42
     साझे
    0.42
     नाखूनों
    0.42
    pecific
    0.41
     राज्यों
    0.40
     基
    0.40
    ၜ
    0.40
    股份
    0.40
    POSITIVE LOGITS
     unforgettable
    0.44
     there
    0.43
    ्वेस्ट
    0.42
    𝟎
    0.41
     investigator
    0.41
    WIN
    0.40
     Investigator
    0.40
    0.38
     Sending
    0.38
     Miriam
    0.38
    Activations Density 0.000%

    No Known Activations