© 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. 165387
    Prev
    Next
    INDEX
    Explanations

    measurements and foreign languages

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

    technical terms

    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
    parsedBlock
    0.48
    reportBody
    0.46
    ⅾ
    0.45
    的内容
    0.45
    但这
    0.45
    ত্রে
    0.44
    在那里
    0.43
    并在
    0.42
    Ν
    0.42
    Но
    0.42
    POSITIVE LOGITS
     elution
    0.52
     measurements
    0.51
     सामान
    0.49
     තා
    0.49
     appliances
    0.47
     decay
    0.46
     پڑھ
    0.46
     mesures
    0.45
     puoi
    0.44
     medidas
    0.44
    Activations Density 0.000%

    No Known Activations