© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11388
    Prev
    Next
    INDEX
    Explanations

    UI layout structure

    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
     with
    -1.26
     as
    -1.13
     to
    -1.10
     which
    -1.07
     or
    -1.07
     and
    -1.07
    謡
    -1.06
    عط
    -1.05
     on
    -1.02
     from
    -1.02
    POSITIVE LOGITS
     dök
    1.07
     fantasi
    1.02
     göm
    1.02
     subsequ
    0.98
     diki
    0.98
     seksi
    0.95
     kapak
    0.93
    取决
    0.93
     сейчас
    0.92
     usu
    0.91
    Activations Density 0.002%

    No Known Activations