© 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. 20918
    Prev
    Next
    INDEX
    Explanations

    cases in, She graduated

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

    speed, height, health

    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
     M
    0.50
    。
    0.46
    '
    0.42
     L
    0.42
    ">
    0.39
     Malibu
    0.38
    </th>
    0.37
     O
    0.37
     obeys
    0.37
     replen
    0.37
    POSITIVE LOGITS
    癃
    0.55
    刓
    0.54
     Danach
    0.51
    慗
    0.48
    வியல்
    0.45
    OfString
    0.45
     വർ
    0.45
     टेंस
    0.45
     आल्सो
    0.44
    ጨም
    0.44
    Activations Density 0.000%

    No Known Activations