© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 68186
    Prev
    Next
    INDEX
    Explanations

    service or core function

    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
    Etimología
    -1.40
     repuesto
    -1.32
    為に
    -1.30
    ができます
    -1.30
    をしています
    -1.30
     redenen
    -1.27
    객체
    -1.27
     medewerkers
    -1.26
     localizar
    -1.25
     materialen
    -1.24
    POSITIVE LOGITS
     for
    2.20
     to
    1.68
     of
    1.67
    s
    1.65
    を
    1.30
    to
    1.24
    x
    1.20
    on
    1.19
    v
    1.16
     on
    1.14
    Activations Density 0.078%

    No Known Activations