© 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. 242416
    Prev
    Next
    INDEX
    Explanations

    alternative phrasing or distinction

    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
    k
    0.51
     Kul
    0.50
     öd
    0.50
     Mos
    0.49
     teore
    0.47
     Jand
    0.47
     eat
    0.46
     our
    0.46
     indicate
    0.46
     ایست
    0.45
    POSITIVE LOGITS
     substitutional
    0.51
     봐야
    0.48
     భాష
    0.47
    ريبي
    0.46
    ల్యే
    0.46
    𒆤
    0.45
    เร็จ
    0.44
    殞
    0.44
    нням
    0.44
    茯
    0.44
    Activations Density 0.000%

    No Known Activations