© 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. 20171
    Prev
    Next
    INDEX
    Explanations

    closing code blocks and punctuation

    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
    䄱
    0.59
    supportsFocus
    0.56
    오
    0.52
    洟
    0.52
    
    0.50
    اردوش
    0.49
    echolog
    0.48
    िलो
    0.48
     Lobkovic
    0.48
    ป่วย
    0.48
    POSITIVE LOGITS
    ].
    0.46
    ,
    0.45
    .
    0.45
    j
    0.45
    ana
    0.44
    ).
    0.43
    io
    0.42
    ios
    0.42
    ;
    0.42
    ior
    0.41
    Activations Density 0.002%

    No Known Activations