© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 6060
    Prev
    Next
    INDEX
    Explanations

    places followed by descriptions

    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_22_width_262k_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
    élix
    0.89
    tså
    0.87
     स्कूली
    0.82
    ამო
    0.81
    Setelah
    0.80
    ತಾ
    0.80
    ܨ
    0.80
    Jika
    0.80
    |=\
    0.79
    Beim
    0.78
    POSITIVE LOGITS
     located
    1.52
     situated
    1.36
     frequented
    1.31
     operated
    1.27
     staffed
    1.24
     nestled
    1.18
     расположен
    1.17
     manned
    1.14
     Located
    1.11
     perched
    1.09
    Activations Density 0.203%

    No Known Activations