© 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. 103943
    Prev
    Next
    INDEX
    Explanations

    food and service variations

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

    promise of or reason for

    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
     الأن
    0.46
    ép
    0.44
    Nicholas
    0.42
    :
    0.42
    ú
    0.41
     واحدة
    0.40
     ബ്രിട്ട
    0.40
     формула
    0.40
    軒
    0.40
    Ins
    0.39
    POSITIVE LOGITS
     diox
    0.48
    ೇತ್ರ
    0.47
     restos
    0.46
    ेडकर
    0.45
     metastases
    0.45
    す楽
    0.45
    তনে
    0.45
     seepage
    0.45
     diode
    0.43
     separating
    0.43
    Activations Density 0.000%

    No Known Activations