© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 162064
    Prev
    Next
    INDEX
    Explanations

    chime design, poetical, Dublín

    np_acts-logits-general · gemini-2.5-flash-lite

    locations, entities, and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    いました
    0.42
    ⟋
    0.42
     होतो
    0.42
     ($\
    0.41
     Indo
    0.41
     आप
    0.41
     మీరు
    0.40
     ď
    0.40
    itochond
    0.40
     [§
    0.40
    POSITIVE LOGITS
    QueryResult
    0.53
    रीन
    0.51
    বিষয়
    0.50
     overflows
    0.49
    RIES
    0.46
    بل
    0.46
    ielles
    0.46
    ALLOW
    0.46
    дің
    0.45
    Artists
    0.45
    Activations Density 0.000%

    No Known Activations