© 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. 71967
    Prev
    Next
    INDEX
    Explanations

    unit | yield

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

    Nets, dolls, thinking, figures, stuff

    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
     حصہ
    0.57
     часть
    0.52
    M
    0.46
    一部分
    0.45
    ња
    0.44
    c
    0.44
    ﻙ
    0.44
     부분
    0.43
    K
    0.43
     части
    0.42
    POSITIVE LOGITS
    艶
    0.46
     converges
    0.45
     épu
    0.45
     lentement
    0.44
    背
    0.44
     mewah
    0.44
    ーツ
    0.43
     episod
    0.43
    awner
    0.43
     tembok
    0.42
    Activations Density 0.000%

    No Known Activations