© 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. 39186
    Prev
    Next
    INDEX
    Explanations

    numbers and names

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

    block external

    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
    '
    0.45
     disadvantage
    0.43
     platform
    0.42
     disaster
    0.42
     adlı
    0.42
     virtual
    0.41
     consortium
    0.41
     a
    0.41
     kriminal
    0.40
     festival
    0.40
    POSITIVE LOGITS
     початку
    0.54
     таксама
    0.51
    Pregnant
    0.47
    干净
    0.45
     বলিয়াই
    0.44
     начиная
    0.43
     толькі
    0.43
     весь
    0.42
     навіть
    0.41
    😤
    0.41
    Activations Density 0.000%

    No Known Activations