© 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. 42737
    Prev
    Next
    INDEX
    Explanations

    chord Queen Graphs 4 <sub>

    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
    0
    1.46
    」
    1.20
     millioner
    1.18
     Barriers
    1.15
    這
    1.15
     這
    1.14
    。
    1.13
    ۔
    1.11
     Hydraulic
    1.06
    Спасибо
    1.06
    POSITIVE LOGITS
    roscopic
    1.22
    the
    1.20
    )=
    1.13
    tle
    1.13
    ról
    1.13
    toluene
    1.10
    لار
    1.09
    nasium
    1.09
    )-
    1.09
    teri
    1.09
    Activations Density 0.000%

    No Known Activations