© 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. 126257
    Prev
    Next
    INDEX
    Explanations

    decimal point

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

    before starting something

    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
    亦
    0.49
    iyati
    0.45
    cesso
    0.44
    另外
    0.43
    意大利
    0.42
    汛
    0.42
    Pseud
    0.40
     호
    0.40
     unfor
    0.40
    샌
    0.40
    POSITIVE LOGITS
     دارید
    0.50
     reread
    0.50
     incrementally
    0.49
     پیدا
    0.49
     describe
    0.48
     excite
    0.47
     discuss
    0.46
     rhythms
    0.46
     使っ
    0.46
     strateg
    0.44
    Activations Density 0.000%

    No Known Activations