© 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. 15179
    Prev
    Next
    INDEX
    Explanations

    of varying size

    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
     others
    -1.26
    が
    -1.16
    という
    -1.16
    などを
    -1.09
    と
    -1.08
    など
    -1.06
    tiéndose
    -1.05
     certain
    -1.04
     such
    -1.02
     alluminio
    -1.02
    POSITIVE LOGITS
     also
    1.18
     også
    1.16
    我国
    1.13
     también
    1.09
     What
    1.08
    𝗧
    1.07
    toDouble
    1.05
     նաև
    1.05
    elded
    1.05
     no
    1.05
    Activations Density 0.176%

    No Known Activations