© 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. 47677
    Prev
    Next
    INDEX
    Explanations

    not to, trying to, in France, leave thoughts

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

    political or organizational efforts

    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
     Dw
    0.44
     Turing
    0.41
    ary
    0.41
     তাড়
    0.40
    ߋ
    0.40
    是非
    0.39
     పద
    0.39
    Ｃ
    0.39
     Puch
    0.39
     Puri
    0.38
    POSITIVE LOGITS
     instalaciones
    0.52
     ejercicio
    0.49
     esfuerzos
    0.48
     iniciativas
    0.48
     erkl
    0.47
     aplicações
    0.46
    Interfaz
    0.45
     esforços
    0.45
     exertion
    0.44
     esfuer
    0.44
    Activations Density 0.000%

    No Known Activations