© 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. 25951
    Prev
    Next
    INDEX
    Explanations

    time, sequence, or aspect followed by other 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
     and
    -1.67
     which
    -1.30
    )="
    -1.21
    öhe
    -1.02
     begleiten
    -1.02
     nachdem
    -1.00
     bagaimana
    -0.98
     including
    -0.97
    >().
    -0.97
     podstawie
    -0.97
    POSITIVE LOGITS
     cristianismo
    1.23
     vincula
    1.21
    では
    1.20
    の問題
    1.20
    齟
    1.17
     it
    1.16
     offrir
    1.15
     decorativos
    1.13
    事態
    1.08
    ってみました
    1.07
    Activations Density 0.025%

    No Known Activations