© 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. 67105
    Prev
    Next
    INDEX
    Explanations

    search query

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

    legally enforceable or valid

    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
    bandSize
    0.50
    PosY
    0.48
     Badajoz
    0.48
    %；
    0.47
    stringstream
    0.47
    ßt
    0.47
    écution
    0.46
    istán
    0.46
     Rxf
    0.46
    åller
    0.46
    POSITIVE LOGITS
    𝑖
    0.45
    "
    0.43
     เพียง
    0.43
     rectify
    0.41
    ս
    0.40
     publish
    0.40
     шко
    0.40
    orems
    0.40
    ในช่วง
    0.40
    i
    0.40
    Activations Density 0.000%

    No Known Activations