© 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. 21436
    Prev
    Next
    INDEX
    Explanations

    simple microfiber, just pure, even before, comparable models, this incarnation

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

    detailed explanations or answers

    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
    、
    0.57
    كال
    0.53
     mir
    0.52
     kur
    0.50
     kond
    0.49
     AIR
    0.48
     MFA
    0.48
     oprav
    0.48
     eko
    0.48
    %、
    0.47
    POSITIVE LOGITS
    उत्तर
    0.50
    getExtension
    0.49
     स्कोर
    0.49
    जेंट
    0.48
    agles
    0.47
    inę
    0.46
    ೋಟ
    0.46
    boundaries
    0.46
    ந்த்
    0.45
     Infections
    0.44
    Activations Density 0.000%

    No Known Activations