© 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. 30749
    Prev
    Next
    INDEX
    Explanations

    modern future keep

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

    develop specialized

    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
    лец
    0.47
    腼
    0.47
    llama
    0.47
    ীনে
    0.45
    ousands
    0.45
     aparentemente
    0.45
    itle
    0.45
    ндай
    0.45
    onga
    0.44
    atial
    0.44
    POSITIVE LOGITS
    公
    0.45
    焼
    0.45
     méthode
    0.43
    女生
    0.43
     جميل
    0.42
    Pub
    0.41
     توسط
    0.41
     Gericht
    0.41
    逐
    0.40
     、
    0.40
    Activations Density 0.000%

    No Known Activations