© 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. 22-GEMMASCOPE-RES-131K
    7. 33803
    Prev
    Next
    INDEX
    Explanations

    approaching the end

    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_22/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
    <0xA3>
    -1.02
    Initial
    -0.93
     following
    -0.88
    responseCode
    -0.88
    iriman
    -0.84
     initial
    -0.84
    Eerste
    -0.83
    🚌
    -0.82
     Weiterbildung
    -0.82
     in
    -0.82
    POSITIVE LOGITS
     final
    1.23
     nearing
    1.17
     endgame
    1.13
    接近
    1.11
     approaching
    1.09
     countdown
    1.09
     finale
    1.08
     toward
    1.08
     cuối
    1.08
     towards
    1.07
    Activations Density 0.043%

    No Known Activations