© 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. 16856
    Prev
    Next
    INDEX
    Explanations

    using as, part of, or in relation to

    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
     meski
    0.50
     apesar
    0.49
     meskipun
    0.46
    .
    0.46
     nonostante
    0.46
     akhir
    0.44
     pourraient
    0.44
     femmes
    0.44
     permettre
    0.42
     و
    0.42
    POSITIVE LOGITS
     вместо
    0.49
    denoted
    0.48
     대신
    0.46
    当作
    0.46
     substituted
    0.44
    involved
    0.43
     involved
    0.41
     mobilized
    0.41
    插入
    0.40
    作为
    0.40
    Activations Density 0.017%

    No Known Activations