© 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. 67345
    Prev
    Next
    INDEX
    Explanations

    dates, blues, follow, weather, guarantee

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

    stress, births, damage, disturbing, sleep

    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
     assin
    0.48
     o
    0.46
     aseg
    0.46
    짭
    0.46
     abuse
    0.45
     nunca
    0.45
    ਿਰ
    0.45
     autora
    0.44
     trusty
    0.44
     unless
    0.44
    POSITIVE LOGITS
    焓
    0.50
     Gable
    0.50
     সিরাপ
    0.49
    擀
    0.49
    鸮
    0.48
     Workbench
    0.48
     البنات
    0.46
     Джо
    0.46
    并通过
    0.46
     Piazza
    0.45
    Activations Density 0.004%

    No Known Activations