© 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. 10-GEMMASCOPE-RES-131K
    7. 21401
    Prev
    Next
    INDEX
    Explanations

    my journeyI will

    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_10/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
     espesor
    -1.79
     больших
    -1.59
     ſeveral
    -1.57
     ABSTRACT
    -1.53
     весьма
    -1.52
    </h1>
    -1.52
     ſub
    -1.51
    嗽
    -1.51
     Gelände
    -1.48
     abſ
    -1.47
    POSITIVE LOGITS
     in
    1.93
     at
    1.61
     bär
    1.59
    This
    1.58
     it
    1.57
    参り
    1.55
     will
    1.51
     l
    1.49
     have
    1.49
     volverá
    1.47
    Activations Density 0.018%

    No Known Activations