© 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. 113701
    Prev
    Next
    INDEX
    Explanations

    make changes or summaries

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

    attracting someone

    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
     automobil
    0.47
     orientação
    0.47
     cunoscut
    0.46
    0.45
     büy
    0.45
     certamente
    0.45
     современного
    0.45
     músico
    0.45
    ഋ
    0.45
    
    0.45
    POSITIVE LOGITS
     drafts
    0.44
    批
    0.44
    試合
    0.42
    面白い
    0.42
     summaries
    0.41
    results
    0.41
     bouts
    0.41
     summarizing
    0.41
    解
    0.41
    analyses
    0.41
    Activations Density 0.000%

    No Known Activations