© 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. 40-GEMMASCOPE-2-RES-262K
    7. 27958
    Prev
    Next
    INDEX
    Explanations

    dart code with types

    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_40_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
    umab
    0.43
    \_
    0.38
    ard
    0.38
    ="..."
    0.38
    ㄸ
    0.38
    alı
    0.37
     अमेरिका
    0.37
    наче
    0.37
    ̂
    0.36
     பக
    0.36
    POSITIVE LOGITS
    UINT
    0.45
     Uint
    0.45
    BuildContext
    0.42
    covariant
    0.41
    /{
    0.40
     {
    0.39
     Lens
    0.37
    ,{
    0.37
    वंशी
    0.37
    लेन
    0.37
    Activations Density 0.003%

    No Known Activations