© 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. 32457
    Prev
    Next
    INDEX
    Explanations

    time intervals or preceding lines

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

    numbers and units

    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
    uksia
    0.45
    也没
    0.44
    딪
    0.43
    олові
    0.41
    ellingen
    0.41
    ==============
    0.41
    ującego
    0.40
     charmed
    0.40
    شون
    0.39
    하신
    0.39
    POSITIVE LOGITS
     เหลือ
    0.44
    +
    0.43
    '
    0.43
     preceding
    0.42
    hrs
    0.42
     precede
    0.42
     قب
    0.42
     rada
    0.42
     vorher
    0.40
     предше
    0.40
    Activations Density 0.104%

    No Known Activations