© 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. 194541
    Prev
    Next
    INDEX
    Explanations

    business contexts

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

    risk level (Low, Medium, High)

    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
     προ
    0.52
     compat
    0.49
    初
    0.49
     amores
    0.49
     enjo
    0.47
     ከአ
    0.47
    جة
    0.46
    어
    0.46
    예
    0.46
     compatibles
    0.45
    POSITIVE LOGITS
    umbuhan
    0.53
    тың
    0.48
    swing
    0.48
    dough
    0.48
     মণ্ডল
    0.48
    distinct
    0.46
     मींस
    0.46
    та
    0.46
    cad
    0.46
     अम्ब
    0.45
    Activations Density 0.000%

    No Known Activations