© 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. 88800
    Prev
    Next
    INDEX
    Explanations

    technical definitions

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

    technical terms and commands

    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
     нама
    0.45
     slalom
    0.44
    وع
    0.43
    льд
    0.42
    кте
    0.42
     partake
    0.42
    太太
    0.42
    ⺝
    0.42
     agres
    0.41
    效益
    0.41
    POSITIVE LOGITS
    imilar
    0.49
    Accept
    0.48
     ---------
    0.47
    cci
    0.46
    Moved
    0.46
    ette
    0.45
    elic
    0.44
    aro
    0.44
     -----------
    0.44
     暗
    0.44
    Activations Density 0.000%

    No Known Activations