© 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. 224948
    Prev
    Next
    INDEX
    Explanations

    availability and options

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

    non-english text

    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
    }";
    0.50
    ܬ
    0.48
     ADMIN
    0.47
    efeu
    0.46
    amazonaws
    0.46
     પાણી
    0.46
     Carmel
    0.45
     collectively
    0.45
    IVAL
    0.44
    餛
    0.44
    POSITIVE LOGITS
    чен
    0.59
     ٹیکسٹ
    0.52
     قوانین
    0.52
     psyk
    0.48
    ﭑ
    0.48
     gestalt
    0.47
    PhotoMode
    0.46
    وترات
    0.46
     negar
    0.46
     gewinnen
    0.45
    Activations Density 0.002%

    No Known Activations