© 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-65K
    7. 62039
    Prev
    Next
    INDEX
    Explanations

    class definitions

    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
    মাকে
    0.41
     occurrences
    0.40
    amment
    0.40
    ień
    0.39
    ᔾ
    0.39
     ascension
    0.38
    u
    0.38
     entering
    0.38
     variances
    0.38
    茹
    0.38
    POSITIVE LOGITS
    ד
    0.46
    ס
    0.45
    Ûn
    0.43
    דו
    0.42
    𝙨
    0.42
    tailed
    0.41
     sekret
    0.41
    ంటారు
    0.41
    ש
    0.41
    ך
    0.41
    Activations Density 0.001%

    No Known Activations