© 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. 40-GEMMASCOPE-2-RES-262K
    7. 36313
    Prev
    Next
    INDEX
    Explanations

    state transitions, extended duration

    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
    트를
    0.46
    რც
    0.44
    起こ
    0.40
     Disqus
    0.40
     avoir
    0.39
     쓰
    0.39
    도를
    0.39
     doet
    0.39
     состоянии
    0.39
    ])]
    0.38
    POSITIVE LOGITS
     Differentiation
    0.39
     Using
    0.38
    SUS
    0.38
     อาจ
    0.37
    PRS
    0.37
    ledem
    0.37
     علاوه
    0.36
     Equipped
    0.36
    persky
    0.36
    PSS
    0.36
    Activations Density 0.000%

    No Known Activations