Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 4735
    Prev
    Next
    INDEX
    Explanations

    using System.Linq;

    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
     and
    0.84
    are
    0.76
    ફેદ
    0.76
    ﻫ
    0.75
    لا
    0.73
     for
    0.71
    <0x8D>
    0.71
    há
    0.71
    <0x89>
    0.71
    <0xAB>
    0.70
    POSITIVE LOGITS
    ס
    1.23
    ன
    1.16
    </strong>
    1.14
    ่
    1.09
    ו
    1.01
    </span>
    1.00
    ש
    1.00
    </b>
    0.99
    ك
    0.98
    </em>
    0.97
    Activations Density 0.001%

    No Known Activations