© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 110072
    Prev
    Next
    INDEX
    Explanations

    building blocks or first steps

    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_31_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
    Easing
    0.45
     negativas
    0.44
     enumerated
    0.43
     scanty
    0.43
    Ꮠ
    0.43
     celebrado
    0.42
    </sup>
    0.41
    Low
    0.41
    েনি
    0.40
    Mua
    0.40
    POSITIVE LOGITS
     내
    0.51
     quale
    0.49
     Punt
    0.49
     ম্যাচের
    0.46
    及び
    0.46
    стере
    0.45
     لیکن
    0.45
    鬪
    0.44
    гы
    0.43
    genome
    0.43
    Activations Density 0.000%

    No Known Activations