© 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. 91472
    Prev
    Next
    INDEX
    Explanations

    needle topstitch and sits on

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

    leftover chicken

    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
    ﾔ
    0.44
    t
    0.42
    weighted
    0.42
     Ци
    0.41
    いくつかの
    0.40
    ionale
    0.39
    partners
    0.39
     ट्रै
    0.39
    acirc
    0.39
    ontal
    0.38
    POSITIVE LOGITS
     automobil
    0.50
     mavi
    0.49
     autonomia
    0.49
     ennemis
    0.48
     बेंगलुरु
    0.46
    冻
    0.44
     atletas
    0.44
     votre
    0.43
    ایت
    0.43
     isk
    0.43
    Activations Density 0.000%

    No Known Activations