© 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. 526
    Prev
    Next
    INDEX
    Explanations

    qualitative descriptors of importance

    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
    もしくは
    1.01
    或是
    0.95
     alebo
    0.95
    あるいは
    0.94
    atau
    0.92
     možda
    0.91
    或者是
    0.89
    或
    0.88
    或许
    0.87
     Atau
    0.85
    POSITIVE LOGITS
     everywhere
    1.34
     anytime
    1.32
     regardless
    1.28
     every
    1.28
     cualquier
    1.26
     any
    1.25
    !
    1.24
     anywhere
    1.22
     nowadays
    1.16
     любого
    1.16
    Activations Density 0.326%

    No Known Activations