© 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. 1783
    Prev
    Next
    INDEX
    Explanations

    JavaScript files

    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
     Бог
    0.22
    ంచరీలు
    0.21
     obstetric
    0.21
     putative
    0.21
    thisTrack
    0.21
    <unused1111>
    0.21
    avacanam
    0.21
     животных
    0.21
    醣
    0.21
    spacePad
    0.20
    POSITIVE LOGITS
    。
    0.36
     using
    0.35
    を使用
    0.34
    With
    0.31
    を実行
    0.31
    ，
    0.31
    使用
    0.30
     with
    0.30
    Using
    0.30
     verwenden
    0.30
    Activations Density 2.039%

    No Known Activations