© 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. 138048
    Prev
    Next
    INDEX
    Explanations

    forward direction

    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
     ホイール
    0.59
    ',"
    0.59
     Finance
    0.59
     Financial
    0.58
    ’
    0.57
    टीसी
    0.57
    meck
    0.55
    ն
    0.55
    Bigr
    0.55
     Fin
    0.55
    POSITIVE LOGITS
     সামনে
    0.61
     establishes
    0.61
     forbids
    0.61
    é
    0.61
    Você
    0.59
     фор
    0.58
     protons
    0.58
     vorne
    0.57
    Vous
    0.55
    functie
    0.54
    Activations Density 0.020%

    No Known Activations