© 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. 102856
    Prev
    Next
    INDEX
    Explanations

    went or go

    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
    </b>
    -0.84
     usando
    -0.82
    tled
    -0.82
    ENDENT
    -0.82
    行政区划
    -0.81
    REFERENCES
    -0.80
    にも
    -0.80
    それも
    -0.79
    窳
    -0.79
    books
    -0.78
    POSITIVE LOGITS
     ahead
    1.07
     unnoticed
    1.04
     Otros
    0.95
     acompañado
    0.95
     along
    0.91
     Ahead
    0.90
     astray
    0.89
    Merry
    0.87
     Viene
    0.82
     against
    0.81
    Activations Density 0.004%

    No Known Activations