© 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. 3695
    Prev
    Next
    INDEX
    Explanations

    utilize something

    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
    s
    1.74
    ни
    1.24
    ﺪ
    1.21
    大
    1.13
    ви
    1.10
    نا
    1.09
    ну
    1.05
    い
    1.05
    пи
    1.04
    ナ
    1.02
    POSITIVE LOGITS
    .
    1.27
    ت
    1.19
    EM
    1.18
    )
    1.13
     it
    1.12
    ang
    1.11
    UR
    1.09
    ין
    1.09
    od
    1.06
    ’
    1.05
    Activations Density 0.026%

    No Known Activations