© 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. 105897
    Prev
    Next
    INDEX
    Explanations

    generated offline

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

    situation, frequency, output

    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
     पर
    0.45
     conception
    0.44
     Constru
    0.43
     चाहे
    0.42
     множество
    0.41
     часа
    0.41
    僉
    0.41
    创立
    0.40
     ох
    0.40
     overkill
    0.39
    POSITIVE LOGITS
    రుపు
    0.47
     স্পর্শ
    0.44
     begitu
    0.43
    နှုန်း
    0.42
    textcolor
    0.42
    glColor
    0.42
    ീകരിച്ച
    0.41
     vermelho
    0.41
    ப்பினர்
    0.41
    
    0.40
    Activations Density 0.001%

    No Known Activations