Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B
    3. 29-GEMMASCOPE-2-RES-16K
    4. 3118
    Prev
    Next
    INDEX
    Explanations

    casting, calling, mixing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    <unused2204>
    0.87
    opportunities
    0.84
    visitors
    0.82
    Mom
    0.81
     opportunities
    0.80
     visitors
    0.78
     goodness
    0.76
     motherhood
    0.76
     terrific
    0.76
     amidst
    0.75
    POSITIVE LOGITS
    你说
    1.33
     OP
    1.19
     @
    1.17
     его
    1.14
    楼主
    1.13
    他说
    1.10
     :/
    1.05
    他說
    1.04
     ppl
    1.02
     hắn
    0.99
    Activations Density 0.510%

    No Known Activations