© 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. 65116
    Prev
    Next
    INDEX
    Explanations

    start of phrases with common words

    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
     these
    -1.60
    these
    -1.34
     estos
    -1.26
     it
    -1.25
    這些
    -1.13
     this
    -1.09
     others
    -1.09
    haped
    -1.07
     Einzelnen
    -1.06
     solchen
    -1.05
    POSITIVE LOGITS
    大丈夫です
    0.97
    LookAnd
    0.96
    はもう
    0.94
    BrowserModule
    0.93
     мину
    0.93
     fieldNum
    0.92
    jścia
    0.91
     FINALLY
    0.91
    //!
    0.90
    “
    0.89
    Activations Density 0.043%

    No Known Activations