© 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. 66128
    Prev
    Next
    INDEX
    Explanations

    actually or actual

    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
     любы
    -0.95
     endforeach
    -0.94
     richi
    -0.93
    Excellent
    -0.92
     orice
    -0.91
    nargs
    -0.90
    Licz
    -0.88
    haviours
    -0.87
     any
    -0.86
     raccomand
    -0.85
    POSITIVE LOGITS
     actually
    1.74
     instead
    1.70
     semblance
    1.44
     действительно
    1.44
     tatsächlich
    1.43
    而不是
    1.38
     actual
    1.33
     faktiskt
    1.31
     Instead
    1.30
     वास्त
    1.30
    Activations Density 0.053%

    No Known Activations