© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2945
    Prev
    Next
    INDEX
    Explanations

    refers to, holding, own tissues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
    '
    1.89
     on
    1.83
    ’
    1.82
     (
    1.79
     both
    1.78
     onto
    1.74
     the
    1.67
    www
    1.65
    ‘
    1.64
     were
    1.64
    POSITIVE LOGITS
    rinsic
    2.34
    许可证
    2.08
     وین
    1.95
    <unused937>
    1.95
    <unused1238>
    1.86
     femin
    1.83
    <unused1874>
    1.83
    abhut
    1.82
    ولز
    1.80
    氩
    1.80
    Activations Density 0.065%

    No Known Activations