© 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. 34-GEMMASCOPE-RES-131K
    7. 107764
    Prev
    Next
    INDEX
    Explanations

    provides information and details

    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_34/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
    ˾
    -1.23
    ånga
    -1.14
     Tư
    -1.09
    ytale
    -1.05
    poptosis
    -1.02
     bedankt
    -0.99
    thè
    -0.98
    İN
    -0.97
    classify
    -0.96
     keď
    -0.96
    POSITIVE LOGITS
     a
    3.36
     details
    2.45
     an
    2.23
     information
    1.83
     detailed
    1.71
    details
    1.46
     détails
    1.46
    Details
    1.46
     some
    1.41
     examples
    1.38
    Activations Density 0.144%

    No Known Activations