© 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. 13999
    Prev
    Next
    INDEX
    Explanations

    . followed by a word

    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
     really
    -1.65
     although
    -1.43
    although
    -1.36
     actually
    -1.30
    Although
    -1.11
     realmente
    -1.08
     aunque
    -1.07
     vraiment
    -1.05
     important
    -1.04
     seemed
    -1.03
    POSITIVE LOGITS
    .../
    1.05
    🤦
    0.98
    🤷
    0.93
    CEL
    0.92
    :))
    0.92
    hilfe
    0.92
    恸
    0.90
    HAHAHAHA
    0.89
    😂😂😂😂
    0.89
     montagnes
    0.88
    Activations Density 0.046%

    No Known Activations