© 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. 209171
    Prev
    Next
    INDEX
    Explanations

    your attention or minors

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

    descriptions and 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
     splits
    0.48
    롯
    0.47
    伙
    0.46
    젹
    0.45
    翰
    0.45
     millió
    0.44
     milion
    0.43
    疗
    0.43
     validations
    0.43
     breathes
    0.43
    POSITIVE LOGITS
     Fallout
    0.49
     Nightmare
    0.48
    کز
    0.47
     ABOVE
    0.45
     Pulau
    0.45
     NaCl
    0.45
     Tanah
    0.44
     aftermath
    0.44
    ukaemia
    0.44
     выше
    0.43
    Activations Density 0.001%

    No Known Activations