© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11988
    Prev
    Next
    INDEX
    Explanations

    separators followed by specific words

    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
    Ī
    0.70
    ))
    0.52
    É
    0.52
    za
    0.49
    Ĭ
    0.47
    INA
    0.46
    GI
    0.46
    Á
    0.46
    Б
    0.45
    Ä
    0.44
    POSITIVE LOGITS
    <unused664>
    0.67
    <unused595>
    0.61
    <unused1085>
    0.61
    <unused1020>
    0.60
    <unused626>
    0.60
    <unused147>
    0.59
    <unused387>
    0.59
    <unused616>
    0.59
    <unused757>
    0.58
    <unused1062>
    0.57
    Activations Density 0.000%

    No Known Activations