© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2397
    Prev
    Next
    INDEX
    Explanations

    technologies and programming languages

    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
    மைக்
    2.51
    statusbar
    2.41
    ETARY
    2.38
    ிடம்
    2.26
    ᵒ
    2.25
    Grid
    2.23
     venenatis
    2.20
    Thai
    2.19
    மையை
    2.18
    மைய
    2.16
    POSITIVE LOGITS
    рг
    2.12
     mnemonic
    2.04
    ර්ශ
    2.03
     blasts
    2.02
    脹
    2.01
     par
    1.95
     "?"
    1.94
     crater
    1.92
    ్రియ
    1.92
     outbursts
    1.89
    Activations Density 0.281%

    No Known Activations