© 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. 9590
    Prev
    Next
    INDEX
    Explanations

    "the" or "el" followed by noun

    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
    0.52
     to
    0.41
     ::
    0.34
    ium
    0.34
    uhan
    0.33
    rie
    0.33
     River
    0.32
    iel
    0.32
     {
    0.32
    iri
    0.32
    POSITIVE LOGITS
    in
    0.51
    ↵
    0.42
    ే
    0.42
    ת
    0.41
    ات
    0.34
    গ
    0.34
     memberships
    0.33
    ین
    0.33
    на
    0.32
    де
    0.32
    Activations Density 0.004%

    No Known Activations