© 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. 28461
    Prev
    Next
    INDEX
    Explanations

    predicting outcomes

    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
    다라고
    0.49
     regering
    0.49
    认为
    0.47
    텍
    0.47
     salari
    0.46
    𒍣
    0.45
    现象
    0.45
    مراجع
    0.45
     valori
    0.45
    ósitos
    0.44
    POSITIVE LOGITS
     be
    0.53
    TING
    0.50
    0.48
    は
    0.46
     URL
    0.45
     shorten
    0.44
    Y
    0.44
    に
    0.43
    flies
    0.42
     restructure
    0.41
    Activations Density 0.000%

    No Known Activations