© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65456
    Prev
    Next
    INDEX
    Explanations

    software licenses and code distribution

    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_34/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
     علاقه
    -0.72
     heiligen
    -0.68
     discoveries
    -0.68
    SDS
    -0.66
    Maggie
    -0.65
     Kategorie
    -0.65
    优惠
    -0.64
    rambled
    -0.64
     triumph
    -0.63
    kunjung
    -0.63
    POSITIVE LOGITS
    obenzene
    0.82
     Rocha
    0.76
    Voto
    0.70
     canvases
    0.68
    出版社
    0.64
     standstill
    0.63
    Съ
    0.62
    있
    0.61
    richtet
    0.61
    onymie
    0.61
    Activations Density 0.104%

    No Known Activations