© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 11154
    Prev
    Next
    INDEX
    Explanations

    version numbers

    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
     Са
    1.42
    ˢ
    1.31
    ﺱ
    1.31
    ట
    1.29
    ശാ
    1.25
    ܵ
    1.25
    Са
    1.21
    им
    1.18
    రుగు
    1.17
    లం
    1.16
    POSITIVE LOGITS
    2
    1.52
    3
    1.48
    7
    1.41
    0
    1.38
    5
    1.38
     Versions
    1.36
     Version
    1.35
    9
    1.35
    8
    1.34
    4
    1.34
    Activations Density 0.064%

    No Known Activations