© 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. 5486
    Prev
    Next
    INDEX
    Explanations

    brief synopsis, facing us, key themes, more linear

    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
    ו
    0.62
     neka
    0.55
     tipo
    0.48
     mesma
    0.47
     unui
    0.47
    r
    0.46
     andra
    0.46
     zid
    0.46
    وید
    0.46
     kole
    0.46
    POSITIVE LOGITS
     EVP
    0.47
     domic
    0.45
     VU
    0.45
    ography
    0.45
    幕
    0.44
     inhabit
    0.44
     HW
    0.43
     superficially
    0.43
     secretions
    0.42
    aird
    0.42
    Activations Density 0.000%

    No Known Activations