© 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. 86803
    Prev
    Next
    INDEX
    Explanations

    calculating numerical questions

    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
    (
    0.80
    0.76
     is
    0.75
    ров
    0.72
    <
    0.71
    \
    0.68
     to
    0.63
     produ
    0.62
    ር
    0.61
    }
    0.57
    POSITIVE LOGITS
    ı
    1.04
     cambió
    0.82
     ຫຼື
    0.82
    ıya
    0.79
     በጣም
    0.77
     こちら
    0.77
     необхідно
    0.77
     เนื่องจาก
    0.77
    <unused2218>
    0.76
    <unused1075>
    0.75
    Activations Density 0.004%

    No Known Activations