© 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. 191444
    Prev
    Next
    INDEX
    Explanations

    resource, information, guide, expedition, animal, service

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

    more advanced

    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
    End
    0.46
    ուր
    0.43
    Int
    0.43
     ၂
    0.42
    าท
    0.42
     linearly
    0.41
    her
    0.41
    Det
    0.41
     manque
    0.41
     ['*.
    0.41
    POSITIVE LOGITS
    què
    0.52
    tudo
    0.52
     Ashland
    0.51
     Cayenne
    0.49
     indole
    0.49
    パッケージ
    0.48
     rustic
    0.46
    sighted
    0.46
    rustic
    0.46
    ौती
    0.45
    Activations Density 0.000%

    No Known Activations