© 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. 101654
    Prev
    Next
    INDEX
    Explanations

    business needs, benefits offered

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

    weary travelers, Nitrogen, Directive, destroyed, decisions

    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
    Hepin
    0.52
    წი
    0.47
     höch
    0.41
     holl
    0.40
    ᔨ
    0.39
    flies
    0.39
    róleo
    0.38
    鬱
    0.38
     челу
    0.38
    числе
    0.38
    POSITIVE LOGITS
     subsequent
    0.41
    د
    0.41
     RI
    0.40
     Normalmente
    0.40
     Fortress
    0.40
    နိုင်သည်။
    0.40
     related
    0.39
    醌
    0.39
    立方
    0.39
     quoted
    0.38
    Activations Density 0.001%

    No Known Activations