© 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. 196722
    Prev
    Next
    INDEX
    Explanations

    common phrases and collocations

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

    leadership and strategy

    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
     zunächst
    0.48
     /=
    0.45
    /__
    0.45
    ?-
    0.44
     杨
    0.44
    add
    0.44
     przykład
    0.44
     (°
    0.44
     sequester
    0.43
    queryset
    0.43
    POSITIVE LOGITS
     dolphin
    0.48
     शहरा
    0.45
     gulf
    0.44
    רו
    0.43
    Gulf
    0.43
    Θ
    0.43
    रेगा
    0.43
     técnica
    0.42
    த்தும்
    0.42
    ρια
    0.41
    Activations Density 0.000%

    No Known Activations