© 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. 585
    Prev
    Next
    INDEX
    Explanations

    numbered step 1

    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
    ंप
    1.16
     coin
    1.13
     proportional
    1.08
     dems
    1.06
     verke
    1.04
     inkl
    1.03
    맣
    1.00
     burdensome
    0.99
     immer
    0.98
     ganske
    0.98
    POSITIVE LOGITS
    Ж
    1.29
     ステンレス
    1.27
    Steve
    1.26
    Re
    1.25
    What
    1.24
    We
    1.22
    When
    1.22
    To
    1.19
    Frances
    1.18
    Stephanie
    1.18
    Activations Density 0.488%

    No Known Activations