© 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. 16-GEMMASCOPE-2-RES-262K
    7. 4229
    Prev
    Next
    INDEX
    Explanations

    finishing techniques

    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
     on
    1.25
     for
    1.23
    0
    1.16
    the
    1.12
    t
    1.07
    ted
    1.06
     の
    1.02
     or
    1.02
     at
    0.99
     if
    0.95
    POSITIVE LOGITS
    ය
    1.48
    ون
    1.41
    ية
    1.34
    را
    1.34
    리
    1.33
    و
    1.30
    λή
    1.30
    اد
    1.26
    وين
    1.23
    কে
    1.20
    Activations Density 0.006%

    No Known Activations