© 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. 251802
    Prev
    Next
    INDEX
    Explanations

    documents, resources

    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
     กลับ
    0.49
     kredi
    0.48
     regresar
    0.47
    倰
    0.46
     kredit
    0.46
     setengah
    0.46
     преодо
    0.46
     ሳ
    0.45
     क्रेडिट
    0.45
     ఆంధ్ర
    0.45
    POSITIVE LOGITS
    فس
    0.53
    documents
    0.52
    yaw
    0.50
    resx
    0.49
    spath
    0.49
    ص
    0.48
    mosaic
    0.47
    V
    0.47
    resources
    0.47
    miot
    0.47
    Activations Density 0.000%

    No Known Activations