© 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. 158311
    Prev
    Next
    INDEX
    Explanations

    Oxford inhabitants

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

    specific concepts

    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
     sogenannten
    0.48
    ခဲ့
    0.47
     význam
    0.46
    ubwa
    0.45
    💶
    0.45
     literals
    0.44
    loans
    0.44
    urcharge
    0.44
    izards
    0.43
     التج
    0.43
    POSITIVE LOGITS
    ీ
    0.47
     badminton
    0.45
     একটী
    0.45
     congregation
    0.45
     each
    0.43
     delicately
    0.43
    a
    0.42
    an
    0.42
     gracefully
    0.42
    ा
    0.42
    Activations Density 0.003%

    No Known Activations