© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 26789
    Prev
    Next
    INDEX
    Explanations

    Rentry page or investments

    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
    ]=-
    0.54
     dermatitis
    0.50
     compleja
    0.48
     sviluppo
    0.47
     desag
    0.47
     проблема
    0.46
     corrupción
    0.46
     biofilms
    0.46
    ໕
    0.45
    ће
    0.45
    POSITIVE LOGITS
     S
    0.44
    rt
    0.44
    id
    0.42
    thomas
    0.42
    island
    0.41
    ir
    0.41
    ll
    0.41
     Jos
    0.40
     BART
    0.40
     Island
    0.40
    Activations Density 0.001%

    No Known Activations