© 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. 157946
    Prev
    Next
    INDEX
    Explanations

    individuals seeking information

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

    legal/medical terms

    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
    らい
    0.49
     vanqu
    0.48
    वाने
    0.47
     embroiled
    0.46
    诮
    0.46
    ፩
    0.45
    驀
    0.45
    覬
    0.45
    Ꮬ
    0.44
     exhort
    0.44
    POSITIVE LOGITS
     prevents
    0.52
     conforms
    0.48
     glTex
    0.47
     Digestive
    0.47
    UM
    0.46
    UCLEAR
    0.46
    Clinic
    0.45
    feas
    0.44
     régl
    0.44
     análisis
    0.43
    Activations Density 0.001%

    No Known Activations