© 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. 143911
    Prev
    Next
    INDEX
    Explanations

    to before joinwhile before theysharing before thistend before torescue before herselfcartridges before asgroup before you

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

    Persona, disruption, rebellion

    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
    á
    0.54
    alık
    0.49
    aper
    0.49
    şe
    0.48
    〕
    0.47
    ap
    0.47
     ہے
    0.47
     या
    0.46
    ။
    0.46
    ays
    0.45
    POSITIVE LOGITS
     SLR
    0.52
     NETWORK
    0.51
     missionary
    0.49
     radios
    0.47
     TLR
    0.47
     hitter
    0.47
     Coalition
    0.46
     sword
    0.46
     klikken
    0.46
     Afrika
    0.46
    Activations Density 0.000%

    No Known Activations