© 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. 157299
    Prev
    Next
    INDEX
    Explanations

    order, towel, corporate, paw

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

    deleting, excitement, disturbing, periods

    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
     byd
    0.51
    ス
    0.46
    （
    0.45
     jin
    0.44
     ス
    0.44
     l
    0.44
    フレックス
    0.44
    1
    0.44
    用
    0.44
     Jind
    0.44
    POSITIVE LOGITS
    amélioration
    0.53
     ाट
    0.50
    ையைக்
    0.48
    arquivo
    0.48
    arantad
    0.46
    überküloz
    0.46
    ంబేద్
    0.46
    没事
    0.46
    maması
    0.45
    ması
    0.45
    Activations Density 0.000%

    No Known Activations