© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67159
    Prev
    Next
    INDEX
    Explanations

    start of dialogue

    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
     this
    -1.52
     when
    -1.34
    beleid
    -1.23
    鈇
    -1.21
    izzazione
    -1.17
     what
    -1.13
    möglichen
    -1.13
     sogenannten
    -1.13
     why
    -1.12
     ketika
    -1.12
    POSITIVE LOGITS
     ARISING
    1.13
    縢
    1.12
    overall
    1.11
     overall
    1.10
    particularly
    1.09
     hadn
    1.09
     relativa
    1.08
    他和
    1.08
    都很
    1.08
    its
    1.08
    Activations Density 0.007%

    No Known Activations