© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 24569
    Prev
    Next
    INDEX
    Explanations

    original works

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    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
    MeshData
    0.42
    pieza
    0.41
    唛
    0.41
     دیتا
    0.38
    ?>"
    0.38
    ?}",
    0.38
     marka
    0.38
    谏
    0.37
    ண்டும்
    0.36
    諫
    0.36
    POSITIVE LOGITS
     propagating
    0.50
     propagation
    0.50
    Prop
    0.49
    prop
    0.48
     Propagation
    0.47
     prop
    0.46
     propagated
    0.46
     Prop
    0.45
     propeller
    0.45
     PROP
    0.44
    Activations Density 0.029%

    No Known Activations