© 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. 71164
    Prev
    Next
    INDEX
    Explanations

    all are

    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
     often
    -1.50
     nhiều
    -1.24
    หลาย
    -1.23
    บาง
    -1.22
     toute
    -1.21
    PENDAHULUAN
    -1.20
     sometimes
    -1.19
     begge
    -1.16
     soms
    -1.16
    erdings
    -1.16
    POSITIVE LOGITS
     that
    1.40
     are
    1.38
    adec
    1.36
     this
    1.36
     except
    1.34
     including
    1.33
     their
    1.29
     entweder
    1.15
    一遍
    1.11
     گفته
    1.10
    Activations Density 0.072%

    No Known Activations