© 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. 128698
    Prev
    Next
    INDEX
    Explanations

    rates appeals / funding requirement

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

    simple code, simplest exchange, both user

    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
     chival
    0.54
    יים
    0.47
    상
    0.45
    🕓
    0.44
    もっと
    0.43
    पृथ्वी
    0.43
    nellement
    0.43
     দিলাম
    0.43
    པ
    0.42
    respArray
    0.42
    POSITIVE LOGITS
     День
    0.52
        
    0.46
                        
    0.46
     Garner
    0.46
     Econ
    0.46
     venez
    0.46
    ценка
    0.43
     До
    0.43
     Census
    0.43
     banding
    0.43
    Activations Density 0.000%

    No Known Activations