© 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. 78708
    Prev
    Next
    INDEX
    Explanations

    end of things

    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
     to
    -1.42
     later
    -0.98
    during
    -0.95
     durante
    -0.93
     during
    -0.88
     challenge
    -0.83
     niektor
    -0.82
     eventually
    -0.81
     alone
    -0.81
     später
    -0.81
    POSITIVE LOGITS
     ✅
    1.15
    DONE
    1.13
    แล้ว
    1.13
    完了
    0.94
     بالنسبة
    0.93
     Finished
    0.93
     satisfactorily
    0.92
     formalities
    0.92
     finished
    0.92
    FINISHED
    0.91
    Activations Density 0.036%

    No Known Activations