© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 111125
    Prev
    Next
    INDEX
    Explanations

    product/service details

    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
     moulds
    0.55
     quadrature
    0.52
     consents
    0.50
     ancestry
    0.49
    ת
    0.49
     aquifers
    0.48
     adverts
    0.48
     scripts
    0.48
     amplifiers
    0.47
    Mobs
    0.46
    POSITIVE LOGITS
     REACH
    0.49
    reeze
    0.48
     लची
    0.47
    float
    0.46
     கடுமையான
    0.46
    ovalent
    0.45
    ambahan
    0.45
    (?:
    0.44
     যদি
    0.44
    olk
    0.44
    Activations Density 0.001%

    No Known Activations