© 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. 184240
    Prev
    Next
    INDEX
    Explanations

    activities and presentations

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

    questions and exclamations

    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
     Wachstum
    0.55
     Königreich
    0.48
    ]=-
    0.47
     Videos
    0.46
     ellipsoid
    0.45
     MHz
    0.45
    inosaur
    0.45
     生命
    0.45
     zehn
    0.45
     museo
    0.45
    POSITIVE LOGITS
     specif
    0.50
    🧁
    0.50
     polémica
    0.47
    구
    0.47
    ﻋ
    0.47
    실
    0.46
     recep
    0.46
    irez
    0.45
     reste
    0.44
    uyên
    0.44
    Activations Density 0.000%

    No Known Activations