© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 140105
    Prev
    Next
    INDEX
    Explanations

    hail damage

    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
     परिजन
    0.48
    zq
    0.47
    a
    0.47
    ᱗
    0.46
     abandoned
    0.46
    闪
    0.46
    ပျ
    0.46
     honoring
    0.45
    蘄
    0.45
     cinnamon
    0.45
    POSITIVE LOGITS
    APDS
    0.53
     دروس
    0.52
    𝐑
    0.52
    ﾞ
    0.52
    VING
    0.50
    RIST
    0.50
    Dragged
    0.49
    ADOW
    0.49
    Sph
    0.49
    affer
    0.48
    Activations Density 0.000%

    No Known Activations