© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11306
    Prev
    Next
    INDEX
    Explanations

    Tor Browser and bridges

    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
     confer
    2.82
     оказа
    2.76
     trimmed
    2.71
     целом
    2.67
    DISPLAY
    2.67
    來越
    2.56
    🏿
    2.50
    🥘
    2.49
    🎒
    2.49
     lowered
    2.49
    POSITIVE LOGITS
    ة
    2.50
    Normdaten
    2.36
    लोनी
    2.31
    ğı
    2.23
    ced
    2.20
    ulus
    2.16
    सायटी
    2.16
    atak
    2.15
    onga
    2.13
    ல்
    2.12
    Activations Density 0.009%

    No Known Activations