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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12262
    Prev
    Next
    INDEX
    Explanations

    AC tour, DNA double, Life insurance, During fabrication

    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
    îtra
    -1.16
     already
    -1.13
     finally
    -1.08
    ძ
    -0.98
    antía
    -0.98
    =[]
    -0.97
    (:,
    -0.94
     dopiero
    -0.94
    input
    -0.93
     =
    -0.93
    POSITIVE LOGITS
     pernah
    1.38
     during
    1.20
     when
    1.13
     plusieurs
    1.12
     by
    1.09
    時代に
    1.08
    اريخ
    1.06
     география
    1.03
     several
    1.01
     عدة
    1.01
    Activations Density 0.008%

    No Known Activations