© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 75154
    Prev
    Next
    INDEX
    Explanations

    `calls for google`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ام
    0.57
    E
    0.57
    am
    0.55
    S
    0.55
    Russian
    0.52
    写真を
    0.52
    at
    0.51
    ال
    0.51
    en
    0.50
    U
    0.50
    POSITIVE LOGITS
     насы
    0.50
     жизнен
    0.49
    PerTrial
    0.48
     주민
    0.48
     μαγγ
    0.47
    갱
    0.47
     adhé
    0.46
     పై
    0.46
     জানান
    0.46
    cích
    0.45
    Activations Density 0.001%

    No Known Activations