© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 36495
    Prev
    Next
    INDEX
    Explanations

    response, Keys, text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
     Еще
    0.86
    و
    0.84
     बढ़िया
    0.82
     Μαρ
    0.82
    сть
    0.82
    妷
    0.81
    ტურ
    0.81
    라고
    0.79
     Baiklah
    0.78
    やお
    0.78
    POSITIVE LOGITS
     usi
    0.93
    ﻛ
    0.88
    '
    0.86
     tasar
    0.86
    4
    0.85
     cui
    0.82
    Hmm
    0.81
     habt
    0.81
     auricul
    0.79
    له
    0.78
    Activations Density 0.000%

    No Known Activations