© 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. 22-GEMMASCOPE-2-RES-16K
    7. 8147
    Prev
    Next
    INDEX
    Explanations

    alphanumeric codes with trailing text

    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_22_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
    ிகளைக்
    0.88
    ionante
    0.87
    llllllll
    0.87
    ⏟
    0.86
    movieId
    0.85
    ………………………………
    0.85
    UniqueIdentifier
    0.83
    ㅑ
    0.82
    avaa
    0.82
    ◹
    0.82
    POSITIVE LOGITS
    R
    0.97
    x
    0.87
    O
    0.84
    T
    0.83
     R
    0.82
    H
    0.82
    L
    0.82
    D
    0.82
    u
    0.81
    У
    0.79
    Activations Density 0.005%

    No Known Activations