© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71166
    Prev
    Next
    INDEX
    Explanations

    not allowed or restricted

    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
     krás
    -1.06
     vaše
    -1.05
    ;*
    -0.99
     zajíma
    -0.98
     detalló
    -0.93
     նաև
    -0.93
     健身
    -0.91
     spannend
    -0.90
     naše
    -0.90
     marcó
    -0.86
    POSITIVE LOGITS
     only
    1.38
     cannot
    1.30
     didn
    1.20
     required
    1.20
     because
    1.16
     do
    1.16
     can
    1.15
     allowed
    1.14
     this
    1.13
     not
    1.05
    Activations Density 0.016%

    No Known Activations