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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 229
    Prev
    Next
    INDEX
    Explanations

    or and

    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_16k_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
    <0x80>
    0.18
     parameter
    0.18
    graphHead
    0.18
     syllable
    0.18
     substring
    0.17
    rafpunkte
    0.17
     thisTrial
    0.17
     ១
    0.17
     dimensionless
    0.17
    AutoStabilise
    0.17
    POSITIVE LOGITS
     and
    0.28
    and
    0.26
    और
    0.24
     ಮತ್ತು
    0.24
     the
    0.23
    the
    0.23
     மற்றும்
    0.22
     và
    0.21
     और
    0.21
     которые
    0.21
    Activations Density 4.928%

    No Known Activations