© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78748
    Prev
    Next
    INDEX
    Explanations

    trunk and torso

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Khat
    -0.72
    転
    -0.68
    typo
    -0.68
     gefe
    -0.66
    setter
    -0.66
    テレ
    -0.64
     إلا
    -0.63
    枸
    -0.63
     گوش
    -0.63
     ベビー
    -0.63
    POSITIVE LOGITS
     trunk
    4.56
     trunks
    3.66
    trunk
    3.53
     Trunk
    3.48
    Trunk
    3.39
     Trunks
    2.48
     tronco
    2.14
     trun
    1.86
    trun
    1.73
     torso
    1.62
    Activations Density 0.057%

    No Known Activations