© 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. 52612
    Prev
    Next
    INDEX
    Explanations

    beautiful pictures

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

    specific actions and categories

    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
     discontinuity
    0.51
    复合
    0.50
    化合物
    0.49
    ᔪ
    0.48
    ייס
    0.48
     injectors
    0.46
    !।
    0.46
    returnValues
    0.46
    ższej
    0.45
     Analysts
    0.45
    POSITIVE LOGITS
     جميعا
    0.45
    licher
    0.44
     لكل
    0.43
    ે
    0.43
    iddag
    0.42
     winter
    0.42
     twee
    0.41
     halen
    0.40
    gene
    0.40
     pol
    0.40
    Activations Density 0.000%

    No Known Activations