© 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. 40821
    Prev
    Next
    INDEX
    Explanations

    mat

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

    XML schemas and SVG points

    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
    льним
    0.52
    ционная
    0.46
    тельность
    0.44
    浸
    0.44
    ટક
    0.43
    拱
    0.43
    짖
    0.43
    さり
    0.43
    ленная
    0.42
    тей
    0.41
    POSITIVE LOGITS
     earned
    0.53
    earned
    0.51
     (\
    0.49
     (++
    0.48
     galore
    0.47
     you
    0.46
     bivariate
    0.46
     multivariate
    0.46
    (%
    0.46
     (;
    0.45
    Activations Density 0.000%

    No Known Activations