© 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. 10-GEMMASCOPE-RES-131K
    7. 13533
    Prev
    Next
    INDEX
    Explanations

    provide or supply arguments

    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_10/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
     eerste
    -1.63
    ğan
    -1.60
     cinquième
    -1.53
     kila
    -1.42
     miroir
    -1.41
     男性
    -1.41
    кин
    -1.41
     firft
    -1.41
     assise
    -1.38
    ：
    -1.38
    POSITIVE LOGITS
     Recently
    2.02
     to
    1.93
     Since
    1.82
     Apparently
    1.76
     recientemente
    1.71
     Perhaps
    1.70
     Furthermore
    1.68
     Surprisingly
    1.67
     Whatever
    1.62
     Gibt
    1.61
    Activations Density 0.039%

    No Known Activations