© 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. 36378
    Prev
    Next
    INDEX
    Explanations

    purchase for

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

    partly, understanding, interact

    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
    ל
    0.52
     seigneur
    0.48
     कैन
    0.48
    মন্ত্র
    0.47
     sufficiently
    0.47
    kého
    0.47
     čo
    0.46
     démon
    0.46
     которым
    0.46
    л
    0.46
    POSITIVE LOGITS
    Vish
    0.52
    Thumb
    0.45
     ቡ
    0.44
     اﻻ
    0.44
     ہمس
    0.43
     Ammonium
    0.42
     Inorg
    0.42
    REE
    0.42
    你就
    0.42
    ROW
    0.41
    Activations Density 0.000%

    No Known Activations