© 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. 16-GEMMASCOPE-2-RES-262K
    7. 31772
    Prev
    Next
    INDEX
    Explanations

    describing styles

    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_16_width_262k_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
    𝑭
    0.75
    𝒌
    0.73
    𝑽
    0.69
    ем
    0.64
    
    0.63
     xWidth
    0.63
    𝒓
    0.61
     направ
    0.61
     일
    0.60
     不过
    0.60
    POSITIVE LOGITS
     is
    0.65
    is
    0.64
     technique
    0.60
    その
    0.58
     correspondent
    0.58
     divulg
    0.58
    —
    0.58
     communique
    0.57
     conveyance
    0.57
     IFC
    0.57
    Activations Density 0.014%

    No Known Activations