© 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. 10609
    Prev
    Next
    INDEX
    Explanations

    what unites us

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

    programming discussion or descriptive 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
     hazır
    0.44
     guerras
    0.44
    वारीत
    0.43
     শান্তিপূর্ণ
    0.42
     guérir
    0.42
    reflectionMap
    0.41
     curing
    0.41
    𒂠
    0.41
     inscripción
    0.40
    ঙ্ঘ
    0.40
    POSITIVE LOGITS
        
    0.47
          
    0.45
    0.44
    <b>
    0.42
       
    0.40
    The
    0.40
           
    0.39
     &
    0.39
     privilege
    0.39
    er
    0.38
    Activations Density 0.000%

    No Known Activations