© 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. 45817
    Prev
    Next
    INDEX
    Explanations

    booking and benefits

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

    clever description of what to remember

    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
    assignments
    0.52
     Za
    0.49
    اد
    0.48
     Chav
    0.48
    ʀ
    0.47
    на
    0.46
    ag
    0.46
    NA
    0.46
    m
    0.46
    signs
    0.45
    POSITIVE LOGITS
    erende
    0.48
     dietro
    0.46
     seseorang
    0.44
     تساوي
    0.44
     dekat
    0.43
     ውሃ
    0.43
    ेन्द्र
    0.43
     بتساوي
    0.42
    内核
    0.42
    ycznej
    0.42
    Activations Density 0.000%

    No Known Activations