© 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. 117246
    Prev
    Next
    INDEX
    Explanations

    presents challenges

    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
    hj
    -0.79
    化する
    -0.79
    stered
    -0.79
    vient
    -0.78
    Explanation
    -0.77
     yaiba
    -0.76
     Ceinture
    -0.74
    ENDER
    -0.73
    ्यों
    -0.73
    𝔼
    -0.73
    POSITIVE LOGITS
     pose
    5.28
     poses
    5.09
     posing
    4.41
     posed
    4.38
     presents
    4.13
     Pose
    3.80
    pose
    3.55
    poses
    3.45
    Pose
    3.39
     presenting
    3.38
    Activations Density 0.245%

    No Known Activations