© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 55703
    Prev
    Next
    INDEX
    Explanations

    kinda stuff

    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
     بسیار
    -1.73
     upon
    -1.47
     perhaps
    -1.43
     Indeed
    -1.41
     indeed
    -1.41
    Indeed
    -1.37
    如此
    -1.32
     již
    -1.30
    非常に
    -1.29
    ówczas
    -1.29
    POSITIVE LOGITS
     kinda
    1.87
     guys
    1.70
     stuff
    1.61
     awesome
    1.52
     maybe
    1.49
    totally
    1.48
     считается
    1.48
     guy
    1.48
    weird
    1.47
     totally
    1.42
    Activations Density 0.119%

    No Known Activations