© 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. 64542
    Prev
    Next
    INDEX
    Explanations

    award recommending

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

    creation of new entities

    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
     recieve
    0.45
    OrderBy
    0.44
    getinfo
    0.44
    getId
    0.44
    getItems
    0.44
     gets
    0.42
    getModel
    0.42
    傌
    0.41
    wellery
    0.41
    ListenAnd
    0.40
    POSITIVE LOGITS
     memes
    0.45
     LaTeX
    0.43
     賞
    0.43
     panelists
    0.42
     Forschungs
    0.42
     TypeScript
    0.42
     kilometers
    0.42
    გრ
    0.41
     contempl
    0.41
     uu
    0.41
    Activations Density 0.000%

    No Known Activations