© 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. 76555
    Prev
    Next
    INDEX
    Explanations

    problems or decisions

    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
    ,
    0.48
     causal
    0.45
     vaste
    0.45
     imedi
    0.39
     zaman
    0.39
     spasmod
    0.39
     impuls
    0.39
     esse
    0.39
     e
    0.38
     reap
    0.38
    POSITIVE LOGITS
    FontFace
    0.40
    itabbo
    0.39
    roffenen
    0.39
     Compatibility
    0.38
     প্রেসিডেন্ট
    0.38
    ণ্ঠে
    0.38
     Regarding
    0.38
     कॉन्फ्रेंस
    0.38
    úblic
    0.38
    BeerItem
    0.37
    Activations Density 0.007%

    No Known Activations