Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 2125
    Prev
    Next
    INDEX
    Explanations

    structural separators and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
    처럼
    0.92
     nœ
    0.92
    <unused2173>
    0.92
    <unused2213>
    0.91
     connaître
    0.89
     più
    0.89
    ⟋
    0.88
     ✓
    0.88
     très
    0.88
     connaît
    0.88
    POSITIVE LOGITS
    untuk
    1.82
    and
    1.81
    this
    1.73
    etc
    1.70
    На
    1.68
    that
    1.66
    would
    1.62
    was
    1.62
    the
    1.62
    of
    1.60
    Activations Density 0.434%

    No Known Activations