© 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. 168477
    Prev
    Next
    INDEX
    Explanations

    witnessed events

    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
     duplo
    0.51
    x
    0.44
    股
    0.42
     matrix
    0.40
     tun
    0.39
     iguais
    0.39
     limitada
    0.39
     gratuits
    0.39
     elles
    0.37
    初心者
    0.37
    POSITIVE LOGITS
     Định
    0.42
     /(
    0.42
    ]=(
    0.41
     Witness
    0.40
     symbolName
    0.40
    Witness
    0.39
     Obtained
    0.38
     witnessed
    0.38
    *=
    0.38
     Coroner
    0.38
    Activations Density 0.001%

    No Known Activations