© 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. 161752
    Prev
    Next
    INDEX
    Explanations

    QMT

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

    archetype, content, texture, reading, anthropomorphic

    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
     RATES
    0.49
    此事
    0.47
    媜
    0.47
     Rates
    0.45
    entlich
    0.44
     ضبط
    0.44
    isation
    0.44
     Contracting
    0.43
     Memorandum
    0.43
    ﻌ
    0.42
    POSITIVE LOGITS
    TextMessage
    0.50
     lavar
    0.48
     podemos
    0.48
     operacional
    0.47
     äh
    0.47
    PWR
    0.46
     powierzchni
    0.46
     ludzie
    0.46
    PlayerSelector
    0.45
     irure
    0.45
    Activations Density 0.009%

    No Known Activations