© 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. 55552
    Prev
    Next
    INDEX
    Explanations

    the dough

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

    turning, prosecuted, uncertain, PDFs

    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
     tabella
    0.47
    novo
    0.46
    మ్
    0.45
    ipers
    0.45
    вна
    0.45
    n
    0.45
    vin
    0.44
     eval
    0.44
    notifications
    0.43
    orda
    0.42
    POSITIVE LOGITS
     tacit
    0.47
     meie
    0.46
     foes
    0.44
    昏
    0.44
    广大
    0.44
     peculiar
    0.43
     hurtful
    0.43
    iliśmy
    0.43
     dissidents
    0.43
     dreary
    0.42
    Activations Density 0.000%

    No Known Activations