© 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. 150334
    Prev
    Next
    INDEX
    Explanations

    kind words

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

    question marks and punctuation

    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
     专业
    0.47
    骆
    0.47
    фии
    0.47
    渔
    0.46
    নীয়
    0.46
     longitudine
    0.46
    િવ
    0.46
     সম্ভবনা
    0.46
    牦
    0.46
     হইয়
    0.45
    POSITIVE LOGITS
    ,
    0.50
     getting
    0.48
    सुक
    0.48
     a
    0.45
    高い
    0.44
    та
    0.44
    いった
    0.44
    いる
    0.43
    getting
    0.42
    .
    0.42
    Activations Density 0.000%

    No Known Activations