© 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. 160176
    Prev
    Next
    INDEX
    Explanations

    after / then / would have

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

    Combining with

    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
    asers
    0.51
    <0x80>
    0.46
    izzie
    0.46
    remen
    0.45
    gers
    0.44
    ungsk
    0.44
    ais
    0.44
     correct
    0.44
    Correct
    0.43
    itches
    0.43
    POSITIVE LOGITS
     evanescent
    0.46
     espress
    0.46
     aŭ
    0.46
     প্রায়
    0.45
     বিদ্য
    0.44
     Eğitim
    0.44
    藓
    0.44
     aggiunto
    0.44
     বাস্তব
    0.43
    logback
    0.43
    Activations Density 0.001%

    No Known Activations