© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 3187
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and specific topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_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
    ال
    0.75
    ш
    0.68
    ق
    0.68
    at
    0.66
    to
    0.66
     إلى
    0.66
    на
    0.66
    ير
    0.66
     een
    0.64
    т
    0.64
    POSITIVE LOGITS
    (
    0.53
     Structures
    0.49
     Although
    0.46
    ლები
    0.44
     adhesions
    0.43
     Headquarters
    0.42
    లు
    0.41
     Using
    0.40
     Programs
    0.40
     Controllers
    0.40
    Activations Density 1.614%

    No Known Activations