© 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. 17-GEMMASCOPE-2-RES-16K
    7. 2169
    Prev
    Next
    INDEX
    Explanations

    diverse language fragments

    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_17_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
    （
    2.06
     (
    2.01
     （
    1.77
    (
    1.75
     (~
    1.71
     ((
    1.70
     (>
    1.65
     ()=>
    1.63
    (=
    1.56
     म्हणजेच
    1.54
    POSITIVE LOGITS
     hadn
    1.55
     habían
    1.49
     había
    1.40
    mıştı
    1.32
    avait
    1.20
    ordum
    1.15
    had
    1.15
    avaient
    1.15
    cadilly
    1.15
     vardı
    1.12
    Activations Density 0.241%

    No Known Activations