© 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. 28179
    Prev
    Next
    INDEX
    Explanations

    want 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
    ：
    0.59
    0.53
    d
    0.52
    かない
    0.45
    行
    0.44
    standalone
    0.43
    が行
    0.42
    r
    0.42
    PS
    0.41
    生成
    0.41
    POSITIVE LOGITS
     opção
    0.60
     என்று
    0.54
     opción
    0.54
     கூறி
    0.53
     என்ற
    0.52
     rencana
    0.52
     ಎಂದು
    0.52
     adlı
    0.52
     कहकर
    0.52
     decreed
    0.51
    Activations Density 0.002%

    No Known Activations