© 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. 1285
    Prev
    Next
    INDEX
    Explanations

    introducing the basis for

    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
    I
    0.95
    9
    0.92
    و
    0.92
    ки
    0.89
     уви
    0.88
     ૩
    0.86
    ных
    0.86
     нажа
    0.86
    𝚘
    0.86
    3
    0.86
    POSITIVE LOGITS
     for
    1.56
    is
    1.18
    س
    1.15
     (
    1.10
    ด
    1.09
    ur
    0.86
    p
    0.85
    ง
    0.85
     For
    0.85
    ク
    0.85
    Activations Density 0.084%

    No Known Activations