© 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. 8958
    Prev
    Next
    INDEX
    Explanations

    providing few examples

    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
    HMS
    1.13
    它
    1.13
    ).)
    1.02
    。《
    1.00
    uhnya
    1.00
    It
    1.00
    。「
    0.99
    。
    0.99
     例文帳に追加
    0.99
    ។
    0.98
    POSITIVE LOGITS
     देखील
    1.38
     mooie
    1.34
     সকল
    1.31
     viele
    1.30
    很多的
    1.30
     firstName
    1.28
     uitgebre
    1.27
     meerdere
    1.24
     birt
    1.24
     MANY
    1.24
    Activations Density 0.197%

    No Known Activations