© 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. 197360
    Prev
    Next
    INDEX
    Explanations

    four pillars

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

    leads to control

    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
    兆
    0.51
    getConfig
    0.50
    мента
    0.50
    Зна
    0.49
    ين
    0.49
     мог
    0.46
    bucket
    0.46
    Да
    0.45
    登
    0.45
    ສາ
    0.45
    POSITIVE LOGITS
     HSV
    0.48
     Furthermore
    0.46
     lightness
    0.46
     Mait
    0.45
     discoveries
    0.44
     Österreich
    0.44
    ANGMAR
    0.44
     discovers
    0.44
    ';
    0.44
     Cai
    0.44
    Activations Density 0.000%

    No Known Activations