© 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. 34-GEMMASCOPE-RES-131K
    7. 109823
    Prev
    Next
    INDEX
    Explanations

    quoted speech

    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_34/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
     
    -1.40
     '/';
    -1.39
    の森
    -1.32
     링
    -1.31
    お試し
    -1.29
    isAlive
    -1.23
    esercito
    -1.20
     折りたたみ
    -1.20
    誰が
    -1.20
    mstyle
    -1.19
    POSITIVE LOGITS
     "
    6.31
     “
    6.09
     „
    3.25
     «
    3.06
     “[
    2.88
    「
    2.84
     ”
    2.84
    “
    2.78
     ``
    2.72
     "[
    2.64
    Activations Density 0.167%

    No Known Activations