© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 2565
    Prev
    Next
    INDEX
    Explanations

    intensifiers followed by descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     árbol
    2.31
    ulatus
    2.06
    мой
    2.04
     Enseñ
    2.03
     metá
    2.02
     আভাস
    2.00
     '|
    1.97
     liné
    1.96
     alcune
    1.95
    crest
    1.94
    POSITIVE LOGITS
     hold
    1.56
    pport
    1.55
    amount
    1.49
    犸
    1.45
    pper
    1.44
    وند
    1.42
    allo
    1.42
    ალურ
    1.40
    쉰
    1.39
    aturamento
    1.39
    Activations Density 0.889%

    No Known Activations