© 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. 169492
    Prev
    Next
    INDEX
    Explanations

    blues jams, years post

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

    social media and continuations

    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
     রিজ
    0.55
    propertyPath
    0.52
    ᱼ
    0.48
    izate
    0.48
    ീസ്
    0.47
     manglid
    0.47
     নির্ধারিত
    0.47
     ஒரே
    0.46
     ಔಷಧ
    0.46
    elementProp
    0.46
    POSITIVE LOGITS
    (
    0.55
    나
    0.51
    रा
    0.51
    ,
    0.50
    기
    0.49
    2
    0.47
    1
    0.46
    라
    0.46
     bureaux
    0.46
     ọ
    0.44
    Activations Density 0.000%

    No Known Activations