© 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. 194088
    Prev
    Next
    INDEX
    Explanations

    measurable Design loans segments trash before markets growing for good

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

    beyond the basics

    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
    াঃ
    0.46
    Didn
    0.44
    an
    0.44
    observed
    0.42
     dennoch
    0.42
    遏
    0.41
    a
    0.40
     আঘাতে
    0.40
    贰
    0.40
    ea
    0.40
    POSITIVE LOGITS
     motorcycl
    0.47
     Hrvatskoj
    0.47
     entice
    0.46
     napp
    0.46
    ',
    0.46
     postpone
    0.46
     realizará
    0.46
     realise
    0.45
    !
    0.45
     Romanian
    0.44
    Activations Density 0.000%

    No Known Activations