© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14209
    Prev
    Next
    INDEX
    Explanations

    each participant

    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
     any
    -1.17
     those
    -1.09
     as
    -1.05
     while
    -1.00
     After
    -0.98
     when
    -0.98
     their
    -0.97
     If
    -0.96
     No
    -0.95
     When
    -0.95
    POSITIVE LOGITS
    共有
    1.41
    Всего
    1.22
    一口气
    1.20
    一共
    1.14
     bawat
    1.13
     groet
    1.05
     каждом
    1.04
     there
    1.03
    EACH
    1.01
     EACH
    0.98
    Activations Density 0.148%

    No Known Activations