© 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. 143585
    Prev
    Next
    INDEX
    Explanations

    coordinates, ratio and ATS formatting

    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
    ન
    0.46
    ーク
    0.44
    blockSize
    0.42
     caravan
    0.42
    ージ
    0.42
    希少
    0.42
     صندوق
    0.41
    renergic
    0.41
     hiker
    0.41
    াজি
    0.40
    POSITIVE LOGITS
     Factories
    0.45
     Elektrokhimiya
    0.44
    냈
    0.44
     tâm
    0.44
    issait
    0.43
     мозга
    0.42
     turnovers
    0.42
    ОВА
    0.41
     Shortly
    0.41
     Towards
    0.41
    Activations Density 0.000%

    No Known Activations