© 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-65K
    7. 65189
    Prev
    Next
    INDEX
    Explanations

    written language, 0xFF bytes

    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_65k_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
    s
    0.66
    izi
    0.44
     overheard
    0.42
     actions
    0.41
     സാഹചര്യ
    0.40
    Ve
    0.40
    ↵
    0.39
    ica
    0.39
     বয়স
    0.36
    u
    0.36
    POSITIVE LOGITS
    чей
    0.48
     ಇದಕ್ಕೆ
    0.46
     subtropical
    0.45
     flexibles
    0.45
    を受
    0.45
     styrene
    0.45
     westbound
    0.45
     stylesheet
    0.44
    ᱔
    0.44
     ㅛ
    0.44
    Activations Density 0.014%

    No Known Activations