© 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. 208284
    Prev
    Next
    INDEX
    Explanations

    titles, teammate, places, mirrors

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

    trading, procedures, proposed solutions

    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
     ciphertext
    0.45
     man
    0.45
     wad
    0.44
     huz
    0.44
    />
    0.44
     zuletzt
    0.44
    viä
    0.43
     meek
    0.43
     hobby
    0.42
     marx
    0.42
    POSITIVE LOGITS
    فاع
    0.49
     юби
    0.48
    옻
    0.46
    cale
    0.45
    <?
    0.45
    łod
    0.44
    韵
    0.44
     ต้อง
    0.43
    樘
    0.43
     Sewage
    0.42
    Activations Density 0.001%

    No Known Activations