© 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. 120583
    Prev
    Next
    INDEX
    Explanations

    words following "not" or "can"

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

    inner dialog and rehearsal

    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
    ab
    0.62
    S
    0.54
    ik
    0.54
    web
    0.54
     we
    0.54
    rest
    0.53
    ig
    0.52
    nian
    0.52
     e
    0.51
    Q
    0.51
    POSITIVE LOGITS
     छा
    0.53
     예상
    0.52
     pecan
    0.49
     pecans
    0.47
     DISABLE
    0.46
     považ
    0.45
     pouvons
    0.45
     시즌
    0.44
     thorny
    0.43
     xây
    0.43
    Activations Density 0.000%

    No Known Activations