© 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. 104662
    Prev
    Next
    INDEX
    Explanations

    islands and complexity

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

    F or GGUF file formats

    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
    paging
    0.49
    nodes
    0.49
    zir
    0.49
    ﻅ
    0.49
    ⓷
    0.49
    ticks
    0.48
     máxim
    0.48
    ين
    0.47
     těž
    0.47
    žić
    0.47
    POSITIVE LOGITS
     Pirate
    0.49
    ร
    0.47
     Spanish
    0.47
     Stelle
    0.46
     Нача
    0.46
     Spaniard
    0.45
     Island
    0.45
     Creative
    0.45
     Hydro
    0.45
     Berl
    0.45
    Activations Density 0.000%

    No Known Activations