© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 41522
    Prev
    Next
    INDEX
    Explanations

    coming together

    np_acts-logits-general · gemini-2.5-flash-lite

    coming together

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     و
    0.91
     ו
    0.76
     但
    0.71
    SI
    0.67
     दट
    0.67
    )
    0.67
     ও
    0.67
    {
    0.66
    及
    0.65
    ier
    0.64
    POSITIVE LOGITS
    i
    1.11
    на
    1.06
    ა
    0.98
    ي
    0.81
    י
    0.81
    até
    0.80
     (
    0.78
    ת
    0.77
    는
    0.76
    ne
    0.75
    Activations Density 0.025%

    No Known Activations