© 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-65K
    7. 16289
    Prev
    Next
    INDEX
    Explanations

    metal and metallic things

    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_65k_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
    絊
    0.48
     عہد
    0.47
     धीमी
    0.47
    كم
    0.46
     indique
    0.46
     الخاص
    0.45
     نرم
    0.45
    ي
    0.45
     قرمز
    0.44
     الخاصة
    0.44
    POSITIVE LOGITS
     metal
    1.36
     metallic
    1.25
    metal
    1.14
    金属
    1.14
    Metal
    1.14
     steel
    1.10
     Metal
    1.10
     метал
    1.10
     METAL
    1.08
    metallic
    1.07
    Activations Density 0.078%

    No Known Activations