© 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. 142430
    Prev
    Next
    INDEX
    Explanations

    older one

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

    love me

    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
    фу
    0.44
    㖪
    0.43
    גר
    0.41
     শিগ
    0.41
    р
    0.41
    ิติ
    0.41
    原子炉
    0.41
    タル
    0.41
    
    0.41
    يذ
    0.40
    POSITIVE LOGITS
    meer
    0.50
     आध्यात्म
    0.49
     perasaan
    0.47
     apologies
    0.44
     bokeh
    0.44
     apology
    0.44
    ✽
    0.44
    communic
    0.43
     ungkap
    0.43
    okkh
    0.43
    Activations Density 0.000%

    No Known Activations