© 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. 9652
    Prev
    Next
    INDEX
    Explanations

    introducing items after "following"

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

    identifications of what follows

    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
     bravo
    0.45
     carefree
    0.45
     ክብ
    0.45
    ை
    0.45
    多了
    0.45
    ：
    0.44
    يار
    0.43
    </h2>
    0.43
    Կ
    0.43
     puterea
    0.42
    POSITIVE LOGITS
     occurred
    0.52
     IELTS
    0.50
     recorded
    0.48
     flowed
    0.48
     reported
    0.47
     gleaned
    0.46
     undergraduate
    0.46
     summarizes
    0.45
     emerged
    0.45
     paraphr
    0.44
    Activations Density 0.013%

    No Known Activations