© 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. 50928
    Prev
    Next
    INDEX
    Explanations

    custom rule or criteria

    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
    崞
    0.49
    晫
    0.45
     UNNEEDED
    0.44
     выше
    0.44
     THESE
    0.43
    线的
    0.43
     Cassie
    0.42
    涩
    0.42
     Chassis
    0.42
     тепер
    0.42
    POSITIVE LOGITS
     świet
    0.48
     implant
    0.44
     scallop
    0.44
     exemplary
    0.43
     subpopulations
    0.43
     spray
    0.43
     surv
    0.42
     água
    0.42
     उत्कृष्ट
    0.42
    چھا
    0.42
    Activations Density 0.013%

    No Known Activations