© 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-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 86428
    Prev
    Next
    INDEX
    Explanations

    hashed passwords and code tokens

    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_53_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
     isothermal
    0.41
    ">-
    0.41
    awah
    0.40
     acetaldehyde
    0.39
    了出来
    0.39
    渡
    0.38
     acetic
    0.38
    Acetic
    0.38
     acetylene
    0.38
    ভাসের
    0.38
    POSITIVE LOGITS
    $
    0.46
     dollars
    0.42
     mengen
    0.42
    Pb
    0.40
    $,
    0.40
     decou
    0.39
     vectors
    0.39
    $=
    0.38
     Manufactured
    0.38
     Serien
    0.38
    Activations Density 0.002%

    No Known Activations