© 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. 97443
    Prev
    Next
    INDEX
    Explanations

    lists and details

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

    portable computer

    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
     нема
    0.49
    ん
    0.49
    нг
    0.48
    iduría
    0.47
    inement
    0.46
     upsetting
    0.46
    きの
    0.44
    큰
    0.43
    метр
    0.42
    seleccion
    0.42
    POSITIVE LOGITS
     Amended
    0.63
     Oral
    0.50
     Targeting
    0.50
     Elektrokhimiya
    0.48
     Routledge
    0.47
     addTask
    0.47
     Niveau
    0.47
     approxim
    0.46
     Keyword
    0.46
     utilisent
    0.46
    Activations Density 0.000%

    No Known Activations