© 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. 201647
    Prev
    Next
    INDEX
    Explanations

    strategies and engagements

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

    steam power mop

    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
    to
    0.55
    4
    0.52
    PIA
    0.48
    browser
    0.45
    6
    0.45
    lens
    0.44
    d
    0.44
    EDI
    0.44
     imageData
    0.44
    UL
    0.43
    POSITIVE LOGITS
     หา
    0.50
     fertiliser
    0.48
    土産
    0.48
     дорого
    0.48
     ยาว
    0.48
     ถ
    0.48
     навча
    0.47
     Lemmas
    0.47
     물질
    0.46
     დიდ
    0.44
    Activations Density 0.002%

    No Known Activations