© 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. 7785
    Prev
    Next
    INDEX
    Explanations

    disclaimers and caveats

    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
    Source
    0.50
    ：
    0.48
    Acrylic
    0.47
     Source
    0.47
    FileName
    0.46
    Mobil
    0.45
    Jou
    0.45
     source
    0.45
    Prompt
    0.44
    Columbia
    0.44
    POSITIVE LOGITS
     ابتد
    0.50
    alaman
    0.48
    𝟭
    0.48
    <unused99>
    0.47
    
    0.46
    捛
    0.46
    invert
    0.46
     nun
    0.46
    𝓸
    0.45
    icides
    0.44
    Activations Density 0.005%

    No Known Activations