© 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. 84698
    Prev
    Next
    INDEX
    Explanations

    individuals are, cost fell, flights to

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

    things and what's needed

    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
     иных
    0.41
    妫
    0.39
    By
    0.39
    Ḵ
    0.39
    και
    0.39
    ning
    0.38
    Altri
    0.38
    枥
    0.38
    จำ
    0.38
    λεύ
    0.38
    POSITIVE LOGITS
     oscill
    0.53
     dieser
    0.51
     homogene
    0.51
     pretrained
    0.48
     Meesho
    0.47
     react
    0.46
     photonic
    0.46
     diseño
    0.46
     crashed
    0.46
     aki
    0.46
    Activations Density 0.003%

    No Known Activations