© 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. 21300
    Prev
    Next
    INDEX
    Explanations

    explaining technical processes and potential impacts

    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
    Ї
    0.49
    琭
    0.45
    ᱤ
    0.43
    FUNCION
    0.43
    че
    0.43
    ystem
    0.42
    ᅨ
    0.42
    ISTRY
    0.41
    InstanceManager
    0.41
    致力于
    0.41
    POSITIVE LOGITS
     audacity
    0.46
     isometric
    0.44
     مختصر
    0.44
     antics
    0.44
     grotesque
    0.43
     Egyptian
    0.43
     -
    0.42
     gutt
    0.42
     phonetic
    0.42
     HTTPS
    0.42
    Activations Density 0.007%

    No Known Activations