© 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. 98532
    Prev
    Next
    INDEX
    Explanations

    cite authorities

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

    automating tasks and grading

    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
    <0x9B>
    0.51
    지
    0.47
     පු
    0.46
    지와
    0.43
     Multin
    0.42
    უდ
    0.42
     khóa
    0.42
    ஷி
    0.42
     lô
    0.42
    يبه
    0.42
    POSITIVE LOGITS
    ession
    0.50
    asse
    0.50
    囃
    0.48
    zal
    0.48
    arlar
    0.48
     सुनवाई
    0.47
    aran
    0.47
    ades
    0.46
     خواهند
    0.46
    ierende
    0.45
    Activations Density 0.000%

    No Known Activations