© 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. 121934
    Prev
    Next
    INDEX
    Explanations

    in following words

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

    Why

    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
     tytu
    0.45
     町
    0.45
     수를
    0.45
     hagas
    0.44
     presos
    0.44
     फंस
    0.43
     hect
    0.43
    芽
    0.42
     belanja
    0.42
     secret
    0.42
    POSITIVE LOGITS
    io
    0.53
    irmat
    0.50
    athery
    0.50
    anyu
    0.49
    resso
    0.49
    arian
    0.48
     في
    0.47
    ة
    0.47
    ية
    0.46
    anean
    0.46
    Activations Density 0.001%

    No Known Activations