© 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. 29966
    Prev
    Next
    INDEX
    Explanations

    Serb Municipalities

    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
     риска
    0.47
    方面
    0.47
    En
    0.42
    ар
    0.42
    Trusted
    0.41
    9
    0.41
    forder
    0.40
     ஒன்ற
    0.39
    ט
    0.39
    Double
    0.39
    POSITIVE LOGITS
     Handic
    0.44
    ㄻ
    0.44
     अवे
    0.44
     Serviços
    0.43
     previsão
    0.43
     calculi
    0.43
     settlor
    0.42
     Empresas
    0.42
     Handicap
    0.41
     Indore
    0.41
    Activations Density 0.001%

    No Known Activations