© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 22627
    Prev
    Next
    INDEX
    Explanations

    just followed by pause or action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ꮦ
    0.47
     slechts
    0.43
     quidem
    0.43
     considerazione
    0.42
     разговор
    0.42
     pronunciation
    0.40
    恂
    0.39
     longitudinale
    0.39
    sembling
    0.39
    вить
    0.38
    POSITIVE LOGITS
    ifiably
    0.53
    \...
    0.49
     THERE
    0.45
     outright
    0.45
    p
    0.45
    …
    0.43
    pp
    0.42
    <0xE8>
    0.41
     BAFF
    0.41
    莫名
    0.41
    Activations Density 0.013%

    No Known Activations