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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 14856
    Prev
    Next
    INDEX
    Explanations

    specific words and their typical followers

    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
    ,
    5.58
    ،
    4.08
    、
    3.82
    ,(
    3.58
    ,
    3.29
     ,
    3.22
    ,,
    3.20
    -,
    3.11
    .,
    3.04
    !,
    3.04
    POSITIVE LOGITS
    <unused1352>
    2.10
    ನಾಡ
    2.00
    <unused1452>
    1.99
    ቝ
    1.98
    <unused1374>
    1.97
    <unused2159>
    1.97
    <unused1366>
    1.96
    <unused1152>
    1.94
    <unused1371>
    1.93
    녃
    1.93
    Activations Density 0.130%

    No Known Activations