© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 75040
    Prev
    Next
    INDEX
    Explanations

    positive or impressive things

    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
    -1.93
     funguje
    -1.10
     same
    -1.09
     příslu
    -1.08
    hoots
    -1.07
     및
    -1.06
    Недоліки
    -1.05
    atient
    -1.04
    Примі
    -1.03
    Actually
    -1.02
    POSITIVE LOGITS
     of
    2.70
     that
    1.95
    чя
    1.29
     sés
    1.13
     neutre
    1.11
     bambou
    1.10
    ális
    1.06
    комплек
    1.06
     မ
    1.05
     vár
    1.05
    Activations Density 0.043%

    No Known Activations