© 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. 208475
    Prev
    Next
    INDEX
    Explanations

    Darwin's theory of evolution

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

    parallel, elaborate, yield

    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
    }_{(
    0.56
    အတွ
    0.55
    ydi
    0.52
     británico
    0.51
    нец
    0.50
     insanın
    0.49
     върху
    0.48
     Брита
    0.48
    şı
    0.47
    
    0.46
    POSITIVE LOGITS
    끔
    0.49
    ه
    0.44
     venen
    0.43
    何
    0.42
    ন্দ
    0.42
    е
    0.41
    eo
    0.41
    焙
    0.40
    靴
    0.39
    هِ
    0.38
    Activations Density 0.001%

    No Known Activations