© 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. 83781
    Prev
    Next
    INDEX
    Explanations

    low key releases

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

    Avoid ambiguity

    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
    번에
    0.57
    번
    0.47
    없는
    0.46
    랫폼
    0.45
    Response
    0.42
    вам
    0.42
    قية
    0.42
    ABLES
    0.42
     ಏ
    0.41
    不定
    0.41
    POSITIVE LOGITS
     IAAF
    0.53
     métall
    0.50
     Investigations
    0.49
     poids
    0.48
     Georgetown
    0.48
     худо
    0.47
     heredit
    0.46
    ič
    0.46
     inscre
    0.46
     supplément
    0.45
    Activations Density 0.000%

    No Known Activations