© 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. 25741
    Prev
    Next
    INDEX
    Explanations

    present study purpose

    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
     without
    -1.18
     this
    -1.12
     that
    -1.07
     every
    -1.02
     any
    -1.02
     from
    -1.00
    langsung
    -0.98
     delivers
    -0.97
    Usuario
    -0.94
     more
    -0.93
    POSITIVE LOGITS
    嗫
    1.13
    ཊ
    1.10
    шир
    1.09
     Repub
    1.02
    Історія
    1.02
     altrimenti
    1.01
     شہر
    1.01
    veness
    1.01
     неф
    1.00
    apparently
    1.00
    Activations Density 0.001%

    No Known Activations