© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 15851
    Prev
    Next
    INDEX
    Explanations

    account security and passwords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ﺔ
    0.42
    ﻛ
    0.40
    쫌
    0.40
    譬
    0.38
     mishaps
    0.37
     ט
    0.37
    যদি
    0.37
    ೧
    0.37
     realistic
    0.36
     щодо
    0.36
    POSITIVE LOGITS
    avor
    0.39
    ou
    0.38
     Modulation
    0.37
     modulates
    0.36
     весь
    0.35
     Presumably
    0.35
    .'
    0.35
     ritmo
    0.35
     volume
    0.34
     respectively
    0.34
    Activations Density 0.001%

    No Known Activations