© 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. 156064
    Prev
    Next
    INDEX
    Explanations

    tulip table

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

    tags, platforms, targeting

    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
     Yukon
    0.54
    l
    0.52
     Hulk
    0.51
    il
    0.50
    ல்
    0.50
     hérit
    0.50
     Allocation
    0.49
     Appalachian
    0.49
    岃
    0.49
    illée
    0.48
    POSITIVE LOGITS
     كما
    0.50
    多少
    0.50
     काफी
    0.48
     pomegranate
    0.46
     흐
    0.46
    味わ
    0.46
     לש
    0.45
    кто
    0.45
    技巧
    0.44
    具体的
    0.44
    Activations Density 0.000%

    No Known Activations