© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99207
    Prev
    Next
    INDEX
    Explanations

    fired or dismissed

    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
    驒
    -2.64
    *
    -2.55
     –
    -2.36
    聍
    -2.34
    锜
    -2.31
    亢
    -2.22
    眨眼
    -2.17
    剜
    -2.14
     scarcely
    -2.14
     didn
    -2.14
    POSITIVE LOGITS
    vège
    2.41
    sekten
    2.38
     pelatih
    2.36
     kjer
    2.33
     Wählen
    2.31
    skar
    2.28
    toja
    2.23
    testen
    2.22
    inä
    2.20
    螓
    2.20
    Activations Density 0.001%

    No Known Activations