© 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. 126331
    Prev
    Next
    INDEX
    Explanations

    qualifying workouts

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

    sexual content, harmful, explicit

    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
    ylene
    0.44
    指導
    0.42
    ž
    0.41
    ๓
    0.41
     homely
    0.40
     horrendous
    0.40
    superuser
    0.39
    lementine
    0.39
    ອງ
    0.39
    FAMILY
    0.39
    POSITIVE LOGITS
    在意
    0.51
     qualifiers
    0.47
     qualifying
    0.47
     Outdoors
    0.47
     Hairst
    0.46
     Airways
    0.45
     contests
    0.45
    屐
    0.45
     workouts
    0.45
     qualifies
    0.44
    Activations Density 0.001%

    No Known Activations