© 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. 121050
    Prev
    Next
    INDEX
    Explanations

    percentages, names, and dates

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

    developing characters

    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
    dat
    0.50
    :*
    0.43
                                   
    0.42
     quantified
    0.42
    Allows
    0.42
    VIEWS
    0.41
    Eug
    0.41
        
    0.41
    និង
    0.40
    :["
    0.40
    POSITIVE LOGITS
     médecins
    0.52
     palais
    0.52
     médecin
    0.51
     mili
    0.49
     yeux
    0.48
     aviones
    0.48
     taux
    0.48
     plaf
    0.47
     abband
    0.47
     città
    0.46
    Activations Density 0.001%

    No Known Activations