© 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. 124641
    Prev
    Next
    INDEX
    Explanations

    WARRANTY issues

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

    place and state

    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
     Greeting
    0.52
     Summer
    0.49
            
    0.48
           
    0.47
    ა
    0.47
    a
    0.46
      
    0.45
                    
    0.45
     ag
    0.45
     ak
    0.43
    POSITIVE LOGITS
    herme
    0.57
     東京都
    0.56
    리카
    0.53
    নান
    0.51
    backgroundColor
    0.50
    निवास
    0.50
    jeta
    0.50
    fireFlower
    0.50
     京都
    0.50
    rafl
    0.50
    Activations Density 0.000%

    No Known Activations