© 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. 11664
    Prev
    Next
    INDEX
    Explanations

    pronouns and names

    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
    sning
    2.35
    ені
    2.26
    ilayer
    2.24
    ğ
    2.23
    이어
    2.22
    ఠ
    2.21
    گە
    2.20
    ена
    2.19
    婳
    2.18
     valoración
    2.16
    POSITIVE LOGITS
     madness
    2.11
     action
    1.96
     insanity
    1.87
    TLE
    1.87
     curl
    1.84
     digits
    1.84
     twitch
    1.81
     arre
    1.80
    ்து
    1.79
     rum
    1.79
    Activations Density 0.002%

    No Known Activations