© 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. 100506
    Prev
    Next
    INDEX
    Explanations

    been successful

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

    breakdown of reasons

    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
    コ
    0.52
    ティ
    0.47
     COMPLEXES
    0.45
    グル
    0.45
     BRAD
    0.45
    ゴ
    0.44
    ig
    0.44
    ガード
    0.43
    オペ
    0.43
     }{
    0.43
    POSITIVE LOGITS
    饷
    0.50
     kutoka
    0.50
    reszt
    0.45
     mif
    0.44
    czas
    0.43
    خيص
    0.43
     Patriotic
    0.43
     వ్యా
    0.42
     Voices
    0.42
    s
    0.42
    Activations Density 0.001%

    No Known Activations