© 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. 22-GEMMASCOPE-RES-131K
    7. 65984
    Prev
    Next
    INDEX
    Explanations

    adjectives followed by nouns

    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_22/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
    metadata
    -0.90
     aguard
    -0.89
     próprio
    -0.89
    mied
    -0.88
     หรือ
    -0.84
     pequeno
    -0.84
    SHIP
    -0.82
    aren
    -0.81
     chamado
    -0.81
     errado
    -0.80
    POSITIVE LOGITS
     "-";
    1.03
    -}
    1.03
    figurine
    1.00
    Comté
    0.94
     fırs
    0.92
     vs
    0.92
    torie
    0.90
     versus
    0.90
     to
    0.90
     and
    0.89
    Activations Density 0.113%

    No Known Activations