© 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-16K
    7. 13129
    Prev
    Next
    INDEX
    Explanations

    like

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

    like with common continuations

    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_16k_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
    ד
    0.63
    ל
    0.53
     litre
    0.52
     ş
    0.51
    ம்
    0.50
     parecen
    0.50
     নই
    0.49
    να
    0.48
    ん
    0.48
     yên
    0.48
    POSITIVE LOGITS
    ius
    0.60
    ịp
    0.58
     There
    0.57
    ipping
    0.55
    There
    0.52
    igma
    0.51
    orsk
    0.51
     प्रकोप
    0.51
    osta
    0.50
    jButton
    0.50
    Activations Density 0.035%

    No Known Activations