© 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. 232323
    Prev
    Next
    INDEX
    Explanations

    you, scoring, pray, vary, negative, America

    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
     fit
    0.43
    dg
    0.41
    per
    0.39
    ø
    0.39
    banner
    0.39
    aturen
    0.38
     меня
    0.38
    دأ
    0.38
    ement
    0.37
     разъ
    0.37
    POSITIVE LOGITS
    ിക്കാ
    0.56
     Designers
    0.51
     Certaines
    0.50
     TES
    0.50
     Suzhou
    0.50
     ANAL
    0.50
     武
    0.49
     Comes
    0.48
     कोत
    0.48
     ადგილ
    0.48
    Activations Density 0.000%

    No Known Activations