© 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. 99821
    Prev
    Next
    INDEX
    Explanations

    response to questions

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

    requirement, 1, no

    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
    reise
    0.46
    bers
    0.44
    $
    0.43
    equilibrium
    0.42
    -+
    0.41
    原始
    0.41
    ING
    0.40
    airline
    0.40
    ing
    0.40
    --
    0.40
    POSITIVE LOGITS
    ForRule
    0.51
     یې
    0.50
     tendrá
    0.48
    就会
    0.47
     poderá
    0.46
     textAppearance
    0.45
    فهام
    0.45
     நிச்சயம்
    0.44
    নার
    0.43
     predecess
    0.43
    Activations Density 0.000%

    No Known Activations