© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 48085
    Prev
    Next
    INDEX
    Explanations

    stacked on

    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/layer_40_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
    咉
    0.40
    痕
    0.38
     patru
    0.38
     nave
    0.38
     deluge
    0.37
     palabra
    0.36
    <0xDB>
    0.36
     સા
    0.36
     devotional
    0.36
     Hey
    0.36
    POSITIVE LOGITS
    Chois
    0.44
    Stencil
    0.43
    Ply
    0.40
    PLY
    0.39
    พล
    0.39
    Gerald
    0.39
    $}}
    0.38
    뚫
    0.38
    தில்
    0.36
    ποί
    0.36
    Activations Density 0.000%

    No Known Activations