© 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. 4381
    Prev
    Next
    INDEX
    Explanations

    time periods and durations

    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
     momentary
    0.37
    が悪
    0.34
    刚才
    0.34
     dvě
    0.33
    arella
    0.33
     at
    0.32
    ika
    0.32
    </h2>
    0.31
     Trevelyan
    0.31
    riend
    0.31
    POSITIVE LOGITS
    🗓
    0.44
     háb
    0.43
     após
    0.42
     después
    0.40
     inspections
    0.39
    بعد
    0.39
     after
    0.39
     بعد
    0.39
     setelah
    0.39
    lagt
    0.38
    Activations Density 0.091%

    No Known Activations