© 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. 219197
    Prev
    Next
    INDEX
    Explanations

    microscopic valleys and price setters

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

    seizures, symptoms, attachment, routines

    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
    冨
    0.57
    рин
    0.53
    佬
    0.52
    λα
    0.49
    説
    0.49
    மது
    0.48
    ام
    0.47
    財
    0.47
    джи
    0.46
    ンダント
    0.46
    POSITIVE LOGITS
    ැල
    0.49
     stick
    0.47
     हों
    0.47
     धरा
    0.46
    <
    0.45
     Yeti
    0.43
     sinter
    0.43
     endlessly
    0.43
     Honda
    0.42
     trig
    0.42
    Activations Density 0.000%

    No Known Activations