© 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. 25337
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
     this
    -1.44
     their
    -1.33
    Ĵ
    -1.22
     such
    -1.21
     its
    -1.19
     even
    -1.10
    humidité
    -1.06
     other
    -1.05
     berguna
    -1.05
    従業
    -1.02
    POSITIVE LOGITS
     prüfen
    1.02
     gebeten
    1.02
    </em>
    0.96
    既然
    0.95
    Mahon
    0.95
     vanden
    0.95
    lepaskan
    0.94
    无论是
    0.94
    WriteBarrier
    0.93
    یکی
    0.92
    Activations Density 0.004%

    No Known Activations