© 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. 64179
    Prev
    Next
    INDEX
    Explanations

    positive outcome or sentiment

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

    consideration, snippets, scope, negative, foreign

    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
    نو
    0.36
    സ്റ്റ
    0.35
     teil
    0.35
     sabbam
    0.35
    াহিনীর
    0.34
     action
    0.34
     "{
    0.34
     extremos
    0.34
    --"
    0.33
    霹
    0.33
    POSITIVE LOGITS
     весьма
    0.43
    の良い
    0.43
     což
    0.42
     Puoi
    0.42
     molto
    0.41
     উপকারী
    0.41
     muy
    0.41
     আমায়
    0.39
     I
    0.39
     लाभदायक
    0.38
    Activations Density 0.000%

    No Known Activations