© 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. 42103
    Prev
    Next
    INDEX
    Explanations

    after or for a duration

    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
     inconvenience
    0.45
     guarante
    0.44
    謁
    0.42
    pluck
    0.40
     높은
    0.39
     perdere
    0.39
     stable
    0.38
     besø
    0.37
     ओवरटाइम
    0.37
     päev
    0.37
    POSITIVE LOGITS
     dwóch
    0.41
    Geometry
    0.40
     сило
    0.40
     Dame
    0.39
    le
    0.38
    aty
    0.38
    obili
    0.38
     =(
    0.38
    ich
    0.38
    iewicz
    0.38
    Activations Density 0.002%

    No Known Activations