© 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. 89463
    Prev
    Next
    INDEX
    Explanations

    allotment next, enhance health, occasion or

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

    mother hen, blocks, sentences, eliminating, betray

    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
    Yz
    0.49
     </
    0.48
    getStringExtra
    0.48
     Акысыз
    0.46
    >*
    0.45
    emitter
    0.45
    ls
    0.45
    )</
    0.44
     THEIR
    0.44
    শ্ম
    0.44
    POSITIVE LOGITS
    不能
    0.47
     منصوبہ
    0.46
     tantos
    0.43
     گھر
    0.43
    ضح
    0.43
    ظر
    0.43
     seguro
    0.43
    ној
    0.42
    牰
    0.42
    ський
    0.41
    Activations Density 0.001%

    No Known Activations