© 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
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 3306
    Prev
    Next
    INDEX
    Explanations

    referring to oneself

    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_17_width_16k_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
     reclam
    2.00
    々
    1.98
     dismin
    1.94
    йте
    1.94
     procedente
    1.89
    Hãy
    1.88
    y
    1.88
     levou
    1.85
    $,
    1.84
     sabores
    1.81
    POSITIVE LOGITS
    т
    2.74
     ভাগ্যবান
    2.64
     popOperand
    2.63
    us
    2.43
    ات
    2.43
    es
    2.38
    verständlich
    2.35
    ת
    2.28
    proclaimed
    2.21
    selves
    2.20
    Activations Density 0.344%

    No Known Activations