© 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. 145823
    Prev
    Next
    INDEX
    Explanations

    states that things are happening

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

    envy, jealousy, foreign words

    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
    Horizontal
    0.56
    Classification
    0.47
    Tanh
    0.46
    Crunch
    0.46
    Linear
    0.45
     létre
    0.45
    互
    0.45
    \")
    0.45
    Hz
    0.44
    Capacity
    0.43
    POSITIVE LOGITS
    ק
    0.57
     envy
    0.54
     доб
    0.54
     coupons
    0.53
     ears
    0.51
     Brescia
    0.50
     villains
    0.49
     jealousy
    0.48
     muchachos
    0.48
     buena
    0.48
    Activations Density 0.000%

    No Known Activations