© 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. 242240
    Prev
    Next
    INDEX
    Explanations

    author interviews

    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
    as
    0.45
    ମ୍
    0.45
    溶液
    0.43
    zeniu
    0.43
    носит
    0.43
    脆弱
    0.42
    с
    0.42
    со
    0.42
    布
    0.42
    ଚ
    0.42
    POSITIVE LOGITS
     waterfall
    0.49
     waterfalls
    0.49
     anore
    0.47
     bushings
    0.46
     enable
    0.46
    ERS
    0.44
     accru
    0.44
     ARN
    0.43
     AUR
    0.43
    ญิง
    0.42
    Activations Density 0.001%

    No Known Activations