© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 204810
    Prev
    Next
    INDEX
    Explanations

    German language specifics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )));
    0.48
     अंतराल
    0.46
     кантип
    0.45
     disseminating
    0.45
    ênt
    0.45
     думаю
    0.45
     restricted
    0.44
     fontsize
    0.44
     tamanho
    0.43
     HOW
    0.43
    POSITIVE LOGITS
    Étienne
    0.48
    șa
    0.46
    ва
    0.45
     Crusade
    0.45
    ja
    0.43
    劳
    0.42
    比赛
    0.40
    θεί
    0.40
    дж
    0.40
    ியம்
    0.40
    Activations Density 0.001%

    No Known Activations