© 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. 25617
    Prev
    Next
    INDEX
    Explanations

    code snippets with this

    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
     then
    -1.59
     that
    -1.48
     parachoque
    -1.47
     וכן
    -1.45
    以上です
    -1.38
    짭
    -1.25
    sprzedam
    -1.24
     esmalte
    -1.24
     konsumen
    -1.22
    uncia
    -1.20
    POSITIVE LOGITS
    The
    1.44
    !
    1.39
    ~
    1.37
     “
    1.33
    の
    1.27
    は
    1.27
    fl
    1.22
    「
    1.21
    “
    1.21
     „
    1.21
    Activations Density 0.002%

    No Known Activations