© 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. 10-GEMMASCOPE-RES-131K
    7. 13408
    Prev
    Next
    INDEX
    Explanations

    closing punctuation

    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_10/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
     here
    -1.16
     manifesting
    -1.14
     about
    -1.14
    𝑿
    -1.13
    gies
    -1.13
    ną
    -1.13
     zeer
    -1.13
    </i>
    -1.12
     \,
    -1.12
    側は
    -1.09
    POSITIVE LOGITS
     ditangkap
    1.35
     to
    1.25
     всегда
    1.21
     our
    1.18
     JOSÉ
    1.16
     rumahnya
    1.15
     annoncé
    1.14
     quelquefois
    1.10
     aceitar
    1.10
     perpé
    1.09
    Activations Density 0.024%

    No Known Activations