© 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. 73473
    Prev
    Next
    INDEX
    Explanations

    no intention 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_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
    愜
    -0.99
     savons
    -0.97
    全体的に
    -0.95
     lavable
    -0.94
    POSIT
    -0.93
    🫁
    -0.90
    せっかく
    -0.89
    ῖς
    -0.87
     gorro
    -0.87
     ALREADY
    -0.87
    POSITIVE LOGITS
     any
    1.40
    ６
    0.94
    政治
    0.93
     ask
    0.91
    ]++;
    0.90
    \},
    0.90
    اضي
    0.90
     hija
    0.88
    ForResult
    0.88
     seeks
    0.86
    Activations Density 0.036%

    No Known Activations