© 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. 10-GEMMASCOPE-RES-131K
    7. 11809
    Prev
    Next
    INDEX
    Explanations

    terms of

    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
    </strong>
    -1.86
    nością
    -1.53
     выбирать
    -1.45
    Personne
    -1.40
    точници
    -1.40
     shield
    -1.40
     separar
    -1.35
    vermögen
    -1.35
     während
    -1.34
     wam
    -1.34
    POSITIVE LOGITS
    O
    1.79
     terms
    1.63
    F
    1.61
    v
    1.55
    b
    1.55
    ta
    1.52
    擷
    1.52
    opheles
    1.51
    $.
    1.51
    ra
    1.51
    Activations Density 0.052%

    No Known Activations