© 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. 33382
    Prev
    Next
    INDEX
    Explanations

    trespass against

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

    non-verbal cues

    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
     a
    0.54
    4
    0.53
     Commandant
    0.50
     CSI
    0.49
    Fue
    0.48
     NOAA
    0.47
    1
    0.47
     H
    0.46
     Bayesian
    0.46
     FEI
    0.46
    POSITIVE LOGITS
     pě
    0.48
    żliw
    0.47
     refugi
    0.47
     honti
    0.46
    주고
    0.46
    ająca
    0.45
    が出来
    0.45
    が出て
    0.45
    
    0.44
     finir
    0.44
    Activations Density 0.000%

    No Known Activations