© 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. 10-GEMMASCOPE-RES-131K
    7. 105781
    Prev
    Next
    INDEX
    Explanations

    Boyd, Bung, Iterable, relatable

    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
    踅
    -2.38
     belki
    -2.30
    蹋
    -2.25
     handlar
    -2.23
     salvación
    -2.22
     raffredd
    -2.19
    ஂ
    -2.19
    驺
    -2.17
    IN
    -2.16
     knap
    -2.16
    POSITIVE LOGITS
    ers
    2.89
    n
    2.66
    (
    2.61
    The
    2.44
    irmanship
    2.30
    er
    2.25
    out
    2.25
    н
    2.19
     leichten
    2.17
    We
    2.14
    Activations Density 0.002%

    No Known Activations