© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 278
    Prev
    Next
    INDEX
    Explanations

    host and boyfriend

    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
    ுள்ளது
    1.37
    ו
    1.28
     구간
    1.25
    ेक
    1.21
    它們
    1.18
    ிறது
    1.17
     SORT
    1.16
     অক্ষর
    1.15
    +"/"+
    1.13
    ்சை
    1.13
    POSITIVE LOGITS
    '
    1.45
    ushka
    1.18
    esses
    1.17
     Emeritus
    1.14
    ship
    1.13
     emeritus
    1.13
    innen
    1.11
    '.
    1.09
    lebnis
    1.09
    ess
    1.07
    Activations Density 1.977%

    No Known Activations