© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 47237
    Prev
    Next
    INDEX
    Explanations

    unauthorized access or disclosure

    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_65k_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
     Maladies
    0.49
    芈
    0.46
    泷
    0.44
     Prend
    0.43
    textAlign
    0.42
     décès
    0.42
    ಿಸಿದರು
    0.41
    ızı
    0.41
    paket
    0.41
     защиту
    0.41
    POSITIVE LOGITS
    d
    0.53
     birch
    0.52
     software
    0.49
     binary
    0.49
     eine
    0.48
     soybean
    0.48
     invites
    0.48
     country
    0.47
     canola
    0.46
     electoral
    0.46
    Activations Density 0.005%

    No Known Activations