© 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. 29468
    Prev
    Next
    INDEX
    Explanations

    numbers and locations

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

    disclaimer: ai cannot provide advice

    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
    는
    0.18
     drugim
    0.16
    기는
    0.15
    نين
    0.15
    बरोबर
    0.15
    崔
    0.15
    습니다
    0.14
     cityName
    0.14
     smatra
    0.14
     самых
    0.14
    POSITIVE LOGITS
     '[
    0.18
    an
    0.17
     ט
    0.17
    Zm
    0.16
    and
    0.16
    broke
    0.16
     Break
    0.16
     ツ
    0.15
     Wharf
    0.15
    bit
    0.15
    Activations Density 0.149%

    No Known Activations