© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 128551
    Prev
    Next
    INDEX
    Explanations

    stock of, absence of

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

    downsides and complexities

    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
     떠
    0.48
    ordial
    0.47
     शूटिंग
    0.47
     자동차
    0.47
     naturale
    0.46
    펴
    0.46
    र्गत
    0.45
     Boats
    0.44
     ಚ
    0.44
     आर्टिफिशियल
    0.44
    POSITIVE LOGITS
    PRODUCT
    0.49
    未必
    0.48
    GRAPH
    0.46
    سب
    0.44
    Lucas
    0.42
    INDEX
    0.42
    LOOK
    0.41
    PERIOD
    0.41
    முத
    0.41
     كثير
    0.41
    Activations Density 0.001%

    No Known Activations