© 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. 39673
    Prev
    Next
    INDEX
    Explanations

    Ione, Iogna, IPS, ion

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

    IA

    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
    0.45
    duh
    0.42
     starry
    0.41
     corals
    0.41
    aworld
    0.40
    Nft
    0.40
    gten
    0.40
     Finger
    0.40
    seven
    0.40
    stoffen
    0.40
    POSITIVE LOGITS
    эл
    0.50
     remplacer
    0.47
     মো
    0.47
    イオン
    0.47
    ケート
    0.47
    ⴹ
    0.46
    รียม
    0.44
    エラー
    0.44
    пиона
    0.43
    functie
    0.43
    Activations Density 0.026%

    No Known Activations