© 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. 60893
    Prev
    Next
    INDEX
    Explanations

    specific entities and events

    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
     preliminar
    -1.16
     MULTIPLE
    -1.12
    的不同
    -1.11
    浓郁
    -1.09
    如下图
    -1.09
     grosso
    -1.09
    albeit
    -1.09
    commonly
    -1.08
     maniere
    -1.07
     अच्छ
    -1.06
    POSITIVE LOGITS
     a
    2.84
     an
    2.22
     not
    1.80
     very
    1.80
     quite
    1.79
     something
    1.72
     difficult
    1.70
     easier
    1.66
     another
    1.63
     important
    1.59
    Activations Density 0.093%

    No Known Activations