© 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. 110560
    Prev
    Next
    INDEX
    Explanations

    comments on posts

    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
     подозре
    -0.94
    توضیحات
    -0.89
    ḵ
    -0.85
    我才
    -0.81
     sufrido
    -0.81
    верь
    -0.81
     cumplido
    -0.80
     широкий
    -0.80
    OE
    -0.80
    ctors
    -0.80
    POSITIVE LOGITS
     comments
    1.11
     there
    1.09
     commenting
    1.08
    newest
    1.00
     says
    0.99
     comment
    0.98
    escaping
    0.96
     آنجا
    0.94
     write
    0.91
     said
    0.90
    Activations Density 0.021%

    No Known Activations