© 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. 128331
    Prev
    Next
    INDEX
    Explanations

    colors, chips, sharing, late fees

    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
    ަށް
    0.46
     budynku
    0.44
    ↼
    0.44
     আইনজীব
    0.44
    ]):
    0.44
    ମ୍
    0.44
     квартире
    0.44
     통해서
    0.42
    ʚ
    0.42
    μορφ
    0.42
    POSITIVE LOGITS
    ods
    0.47
     saman
    0.46
    iv
    0.45
    ali
    0.45
    iken
    0.44
    aren
    0.44
    ische
    0.44
    kins
    0.43
    alia
    0.42
     mitt
    0.42
    Activations Density 0.003%

    No Known Activations