© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 137826
    Prev
    Next
    INDEX
    Explanations

    thoughts when

    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
     проєкту
    0.45
    '>");
    0.45
    IVERS
    0.44
    ા
    0.43
    ताएं
    0.43
    ISTR
    0.43
     காற்ற
    0.42
    שׁ
    0.42
    ENSION
    0.42
     ን
    0.42
    POSITIVE LOGITS
     bien
    0.50
     força
    0.49
     animating
    0.48
    für
    0.46
     Diseño
    0.46
     Marty
    0.45
    9
    0.45
     racked
    0.44
     tost
    0.44
     vor
    0.44
    Activations Density 0.000%

    No Known Activations