© 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. 50988
    Prev
    Next
    INDEX
    Explanations

    structures and concepts

    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
    गेड
    0.48
    Го
    0.46
    ível
    0.45
     Governo
    0.45
    б
    0.43
     والسلام
    0.43
     serão
    0.42
    ाग्राम
    0.42
     Scotland
    0.42
    }=-
    0.42
    POSITIVE LOGITS
     ascertaining
    0.52
     tzv
    0.49
     "'
    0.46
    OLYBD
    0.45
     researches
    0.45
     "\"
    0.45
     istraž
    0.44
     discernment
    0.44
     ছিল
    0.44
    教材
    0.44
    Activations Density 0.016%

    No Known Activations