© 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. 7244
    Prev
    Next
    INDEX
    Explanations

    abstract code identifiers

    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
     =
    0.88
     is
    0.63
        
    0.60
     was
    0.60
            
    0.59
    _
    0.55
    ;
    0.55
    ；
    0.52
       
    0.52
    ="";
    0.51
    POSITIVE LOGITS
     guérir
    0.45
    婦
    0.45
    omyosin
    0.44
    STRAINT
    0.43
    olecules
    0.43
    usetzen
    0.43
    codile
    0.42
    .),
    0.41
    テナンス
    0.41
    oribus
    0.41
    Activations Density 0.059%

    No Known Activations