© 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. 9464
    Prev
    Next
    INDEX
    Explanations

    performance issues

    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
    นะคะ
    1.48
    l
    1.34
    re
    1.31
    lardan
    1.30
    d
    1.29
    m
    1.29
    ন
    1.28
    les
    1.27
     crus
    1.23
    də
    1.23
    POSITIVE LOGITS
    ج
    1.40
    ेल
    1.28
    पी
    1.23
    દ
    1.16
    પ
    1.16
    RANGER
    1.15
    RAIT
    1.15
    گ
    1.15
    RIAL
    1.13
    ö
    1.13
    Activations Density 0.026%

    No Known Activations