© 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. 149463
    Prev
    Next
    INDEX
    Explanations

    identifiers and references

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

    affiliation, cost, section

    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
    ❜
    0.57
    <unused266>
    0.51
    <unused708>
    0.51
     lleva
    0.50
    é
    0.48
    و
    0.48
    <unused428>
    0.47
     önemlidir
    0.47
    <unused423>
    0.46
    <unused1806>
    0.46
    POSITIVE LOGITS
    。
    0.55
     USGS
    0.52
     NGC
    0.49
    ēng
    0.47
    0.47
     anthropogenic
    0.43
     플러스
    0.43
     노
    0.41
     glaring
    0.41
    NGC
    0.41
    Activations Density 0.000%

    No Known Activations