© 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. 189400
    Prev
    Next
    INDEX
    Explanations

    sound area, digital services, assertiveness training

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

    alphabet letter sequences

    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
    يطان
    0.58
    cuits
    0.52
    Izq
    0.52
    ඈ
    0.49
     வெப்சீரி
    0.48
    ⨔
    0.47
    drying
    0.47
     ocurrido
    0.47
    нит
    0.47
    ourent
    0.47
    POSITIVE LOGITS
    後ろ
    0.46
     journal
    0.46
     vessel
    0.46
     ไล
    0.44
     slipper
    0.44
     COMO
    0.43
    ↵
    0.43
     מג
    0.43
     cah
    0.43
     CV
    0.42
    Activations Density 0.000%

    No Known Activations