© 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. 31-GEMMASCOPE-2-RES-262K
    7. 109818
    Prev
    Next
    INDEX
    Explanations

    authentication, tokens, or code

    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_31_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
    写真
    0.50
    сная
    0.49
    さ
    0.49
    ienti
    0.49
    برای
    0.49
    み
    0.48
    Дан
    0.47
    ば
    0.47
    ুরা
    0.45
    Guy
    0.45
    POSITIVE LOGITS
     escalate
    0.52
     денег
    0.49
     turtleneck
    0.44
    ativen
    0.42
     standardize
    0.40
     consom
    0.40
     upheld
    0.39
     notte
    0.39
     haute
    0.39
     maven
    0.39
    Activations Density 0.004%

    No Known Activations