© 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. 138094
    Prev
    Next
    INDEX
    Explanations

    tell us exactly or orally

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

    space, background, downtime

    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
    warn
    0.46
    Kiza
    0.44
    }^{\
    0.44
     usersRouter
    0.42
     دستور
    0.42
    ^{*}}
    0.41
    آپ
    0.41
    wdir
    0.41
     obso
    0.40
     افس
    0.40
    POSITIVE LOGITS
    ま
    0.52
    ICLE
    0.47
    шення
    0.47
    ICES
    0.46
    ICIAL
    0.45
    招生
    0.45
     Xe
    0.44
    άζ
    0.44
     заболевания
    0.43
    IK
    0.43
    Activations Density 0.004%

    No Known Activations