© 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. 128430
    Prev
    Next
    INDEX
    Explanations

    glamorous, glam rock, or clamor

    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
     eſſ
    -2.64
     remarked
    -2.48
    瞜
    -2.47
    ⠜
    -2.47
    哢
    -2.44
    扨
    -2.42
     pubblicità
    -2.39
    蕷
    -2.25
     utilizza
    -2.20
    Donativos
    -2.19
    POSITIVE LOGITS
    .
    3.28
     
    2.38
    0
    2.31
    and
    2.22
     और
    2.11
    e
    2.06
    沨
    2.05
     "
    2.03
    T
    2.02
     glam
    1.99
    Activations Density 0.001%

    No Known Activations