© 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. 157487
    Prev
    Next
    INDEX
    Explanations

    aggressive driving, Chinese New Year, safety officers

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

    findom tasks NSFW

    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
    吸収
    0.53
    Hours
    0.49
    Learning
    0.49
    v
    0.49
    Paw
    0.48
    Uncle
    0.48
    d
    0.48
    য়
    0.47
    مش
    0.47
    Electrical
    0.47
    POSITIVE LOGITS
     méth
    0.57
     souten
    0.54
     率
    0.54
     νη
    0.53
     flaming
    0.52
     serveur
    0.52
     déploy
    0.52
     uprav
    0.52
     nerada
    0.52
     патри
    0.51
    Activations Density 0.000%

    No Known Activations