© 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. 46892
    Prev
    Next
    INDEX
    Explanations

    announce tapped

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

    monomorphization

    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
    aları
    0.49
    鲽
    0.48
    Pyrimidine
    0.46
    முகச்
    0.46
     반응
    0.45
     реакции
    0.45
     često
    0.44
    isComposite
    0.44
     genellikle
    0.43
     많
    0.43
    POSITIVE LOGITS
     egen
    0.46
     terminer
    0.43
    NET
    0.41
    ghe
    0.41
     announced
    0.41
     PLUS
    0.41
     зру
    0.41
     vanity
    0.41
     commer
    0.40
     avoc
    0.40
    Activations Density 0.000%

    No Known Activations