© 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-262K
    7. 13715
    Prev
    Next
    INDEX
    Explanations

    option items

    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_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
     chacun
    0.37
     chacune
    0.37
    போதும்
    0.37
    
    0.34
    🖉
    0.31
     unrival
    0.31
     ஏற
    0.30
     protagonisti
    0.30
     jeder
    0.30
    parvec
    0.30
    POSITIVE LOGITS
     కూడా
    0.46
    También
    0.42
     גם
    0.42
    )
    0.41
     )
    0.39
     även
    0.38
     cũng
    0.38
     даже
    0.38
     methane
    0.37
     також
    0.37
    Activations Density 0.039%

    No Known Activations