© 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. 15522
    Prev
    Next
    INDEX
    Explanations

    EXISTING state or condition

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

    special characters and emojis

    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
    0.50
    থাৎ
    0.44
    L
    0.41
    9
    0.40
    5
    0.40
    antial
    0.40
    8
    0.39
    Ba
    0.39
    getic
    0.39
    7
    0.39
    POSITIVE LOGITS
     TripAdvisor
    0.48
     взгля
    0.43
     හොඳ
    0.41
     теркәлүсез
    0.40
     &/
    0.40
     गाइस
    0.38
     unmistakable
    0.38
    𝗦
    0.38
     පමණ
    0.38
    чке
    0.37
    Activations Density 0.050%

    No Known Activations