© 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. 150853
    Prev
    Next
    INDEX
    Explanations

    to followed by the

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

    duration and evaluation

    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
    лд
    0.51
    áním
    0.51
    ллі
    0.50
    лда
    0.46
    л
    0.46
    ﻟ
    0.46
    න්ට
    0.46
    ليه
    0.45
    лта
    0.45
    મ્પ
    0.45
    POSITIVE LOGITS
     E
    0.61
    t
    0.57
     temps
    0.53
     Labrador
    0.53
     afectar
    0.53
     N
    0.52
     U
    0.52
     enduro
    0.52
     α
    0.50
     Rennes
    0.49
    Activations Density 0.000%

    No Known Activations