© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39285
    Prev
    Next
    INDEX
    Explanations

    words followed by punctuation

    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
     desierto
    -1.16
    🖇
    -1.10
     moverse
    -1.09
    අ
    -1.09
    ậy
    -1.08
    ఙ
    -1.05
    mistak
    -1.02
    ğer
    -1.02
    ᵣ
    -1.02
    écial
    -1.01
    POSITIVE LOGITS
     they
    1.63
     them
    1.48
    ).
    1.47
     it
    1.42
     also
    1.36
     их
    1.23
     their
    1.21
     then
    1.16
    hibitor
    1.15
    ):
    1.11
    Activations Density 0.043%

    No Known Activations