© 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. 150881
    Prev
    Next
    INDEX
    Explanations

    events and tasks

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

    engineering costs and expertise

    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
     haunted
    0.48
     راه
    0.47
     اﻷ
    0.45
    eln
    0.45
    绾
    0.44
     اور
    0.43
     ولي
    0.43
     حیر
    0.42
    ت
    0.42
     soort
    0.42
    POSITIVE LOGITS
    /***
    0.46
    JWT
    0.46
    发
    0.45
    愉快
    0.45
     बढ
    0.44
    만큼
    0.44
     LINE
    0.44
    ମ୍
    0.44
    發
    0.44
    鐵
    0.43
    Activations Density 0.000%

    No Known Activations