© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 187900
    Prev
    Next
    INDEX
    Explanations

    suppliers and products

    np_acts-logits-general · gemini-2.5-flash-lite

    identifying features and their context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    வத
    0.48
    ष्टि
    0.48
    forbidden
    0.48
    实在
    0.46
     выходит
    0.45
     કરવી
    0.45
     probability
    0.43
    苳
    0.43
    后果
    0.43
    妘
    0.43
    POSITIVE LOGITS
    AST
    0.48
     ergonomics
    0.47
     Prisons
    0.46
    OEM
    0.44
     Crimes
    0.43
     önces
    0.43
     unveils
    0.43
    genomes
    0.43
     studded
    0.42
     genomics
    0.41
    Activations Density 0.001%

    No Known Activations