© 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. 169027
    Prev
    Next
    INDEX
    Explanations

    place has, shooter who, lower your

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

    Valenciana, bake, when, moment

    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
    면
    0.45
     ---------
    0.44
     原因
    0.43
    dictionary
    0.43
    دی
    0.43
    
    0.43
     所以
    0.42
     面
    0.42
     此
    0.42
     위의
    0.42
    POSITIVE LOGITS
    smöglichkeiten
    0.56
    খণ্ড
    0.53
     át
    0.52
    økt
    0.50
     specificity
    0.49
     revital
    0.49
     estén
    0.48
     létre
    0.48
     pennies
    0.48
     ressort
    0.47
    Activations Density 0.000%

    No Known Activations