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-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 2299
    Prev
    Next
    INDEX
    Explanations

    abstract nouns and proper nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    !”.
    1.30
     می‌باشد
    1.27
    !);
    1.26
    !");
    1.26
     אשר
    1.22
    !”,
    1.18
    !"));
    1.18
    !!");
    1.17
    )!
    1.17
    !!!");
    1.16
    POSITIVE LOGITS
     amid
    1.19
     _
    1.04
     while
    1.01
     --
    0.95
     ″
    0.95
     "'
    0.94
    elike
    0.94
     among
    0.93
     despite
    0.93
     statewide
    0.90
    Activations Density 0.037%

    No Known Activations