© 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. 25697
    Prev
    Next
    INDEX
    Explanations

    linking lists of advice

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

    principles, applications, brands, tactics

    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
    geschwindigkeit
    0.42
    ږد
    0.40
     Assessing
    0.40
    komst
    0.40
    十七
    0.40
    ската
    0.39
    ❞
    0.39
    диви
    0.39
    
    0.39
     মনো
    0.38
    POSITIVE LOGITS
    thorn
    0.48
     നിങ്ങൾക്ക്
    0.47
     ile
    0.46
     recipient
    0.44
     ise
    0.43
     مسیر
    0.43
    run
    0.43
     കഴ
    0.42
     sprouting
    0.42
     आप
    0.42
    Activations Density 0.000%

    No Known Activations