© 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. 218604
    Prev
    Next
    INDEX
    Explanations

    terms and conditions

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

    guide, control, precise

    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
    вли
    0.46
     построен
    0.46
    帀
    0.44
     kac
    0.44
     satirical
    0.43
     terbentuk
    0.43
     taill
    0.43
    すべて
    0.43
     spel
    0.42
    знав
    0.42
    POSITIVE LOGITS
    _
    0.53
    equipped
    0.50
    en
    0.49
     ಜ
    0.48
    ind
    0.47
    sez
    0.45
    HT
    0.44
    Freq
    0.44
    QUANT
    0.44
    ital
    0.44
    Activations Density 0.000%

    No Known Activations