© 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. 7-GEMMASCOPE-2-RES-16K
    7. 167
    Prev
    Next
    INDEX
    Explanations

    <start_of_turn>model

    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_7_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
    <unused1950>
    2.77
     vattabbam
    2.67
    𒋗
    2.62
    𒌉
    2.61
    𒋢
    2.61
     yojet
    2.60
    <unused1182>
    2.60
    𒁁
    2.59
     paccati
    2.57
    <unused1474>
    2.56
    POSITIVE LOGITS
    fl
    1.52
    un
    1.47
    co
    1.46
    ut
    1.44
    att
    1.43
    oc
    1.37
     c
    1.35
    im
    1.34
    T
    1.33
     t
    1.33
    Activations Density 7.052%

    No Known Activations