© 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. 182223
    Prev
    Next
    INDEX
    Explanations

    information and danger

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

    Whisperwood

    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
     krat
    0.49
    ible
    0.48
     to
    0.46
     poche
    0.46
     Aver
    0.45
     egli
    0.45
    could
    0.44
    惹
    0.44
     Consumers
    0.44
    putting
    0.44
    POSITIVE LOGITS
    化した
    0.43
    үй
    0.42
    取引
    0.41
    ADIAN
    0.41
    交易
    0.41
    กา
    0.41
     सम्पन्न
    0.41
    自身的
    0.40
    FIG
    0.40
    ಗ
    0.40
    Activations Density 0.000%

    No Known Activations