© 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. 684
    Prev
    Next
    INDEX
    Explanations

    receipts, between, down, into

    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
    嬷
    0.42
     কোমল
    0.41
     рр
    0.40
    $)
    0.40
    SimpleDateFormat
    0.40
    ụ
    0.39
    Treasurer
    0.38
     คูณ
    0.38
    ổ
    0.38
    給你
    0.37
    POSITIVE LOGITS
     alterna
    0.53
     arena
    0.52
     निर्माताओं
    0.52
    レ
    0.51
     constru
    0.50
     patrols
    0.50
     liberals
    0.50
     debat
    0.50
    انوي
    0.49
     construction
    0.49
    Activations Density 0.000%

    No Known Activations