© 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. 26213
    Prev
    Next
    INDEX
    Explanations

    loading objects and their destinations

    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
    Had
    -0.94
    нин
    -0.84
    inalg
    -0.84
    Might
    -0.82
     यू
    -0.81
    ဤ
    -0.81
     weakest
    -0.80
    ią
    -0.80
     dovuto
    -0.80
     Ecosystem
    -0.79
    POSITIVE LOGITS
     into
    2.48
     onto
    1.72
     from
    1.29
     vào
    1.16
    onto
    1.05
    必要的
    0.99
     Conselho
    0.99
     unto
    0.96
     Ont
    0.94
    Into
    0.94
    Activations Density 0.099%

    No Known Activations