© 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. 3116
    Prev
    Next
    INDEX
    Explanations

    functions, policies, or states

    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
     camiseta
    0.47
    ']),
    0.45
     রকমের
    0.44
     clor
    0.44
     específico
    0.43
     started
    0.43
     extranj
    0.43
     radia
    0.43
     zmian
    0.42
     DISTRIBUTION
    0.42
    POSITIVE LOGITS
    Marian
    0.46
    First
    0.45
    ᚋ
    0.44
    <0xEF>
    0.44
    汝
    0.43
    
    0.42
    ors
    0.42
     viv
    0.42
    imper
    0.42
     と
    0.41
    Activations Density 0.008%

    No Known Activations