© 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. 50025
    Prev
    Next
    INDEX
    Explanations

    navigates, comfortably hard, clause

    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
     ተጨማሪ
    0.46
     proffered
    0.45
     ಪ್ರ
    0.45
    மேலும்
    0.44
    Fund
    0.43
    設
    0.43
    ¿
    0.43
    ↵↵↵↵↵↵
    0.43
     powodu
    0.43
     prompting
    0.42
    POSITIVE LOGITS
    क्ति
    0.47
     Sexy
    0.44
     Sea
    0.44
    teenth
    0.43
    skap
    0.42
    鐒
    0.42
     modulus
    0.42
     Eclipse
    0.41
    asjoner
    0.41
    书城
    0.41
    Activations Density 0.007%

    No Known Activations