© 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. 4060
    Prev
    Next
    INDEX
    Explanations

    about/regarding topics

    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
     mooi
    0.41
    ،
    0.39
     Сам
    0.39
     وا
    0.39
     ն
    0.39
    }{
    0.38
    }$,
    0.38
     ل
    0.38
     с
    0.37
    }$.
    0.37
    POSITIVE LOGITS
    p
    0.46
    ي
    0.46
    ב
    0.44
    ين
    0.43
    t
    0.43
    ו
    0.42
    f
    0.42
    an
    0.40
    ש
    0.40
    י
    0.40
    Activations Density 0.439%

    No Known Activations