© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14812
    Prev
    Next
    INDEX
    Explanations

    conv stride 1 or 2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    ല്ലാം
    3.08
    чику
    3.00
    ﻓ
    2.91
    چہ
    2.89
    getitem
    2.86
     inhomogeneities
    2.76
    нима
    2.76
    bindo
    2.73
    তনে
    2.70
     Pengh
    2.69
    POSITIVE LOGITS
     }+
    2.81
     logique
    2.44
    ின்ற
    2.43
    өө
    2.41
    bogen
    2.41
    categoryId
    2.39
    arg
    2.38
    und
    2.34
     bao
    2.33
    WithSize
    2.32
    Activations Density 0.002%

    No Known Activations