© 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. 6944
    Prev
    Next
    INDEX
    Explanations

    a lot of

    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
     few
    1.02
     چند
    0.92
     quelques
    0.86
    gever
    0.86
     wenigen
    0.84
     vài
    0.84
    few
    0.82
    ැ
    0.81
     briefly
    0.80
     Few
    0.79
    POSITIVE LOGITS
     lot
    3.44
     LOT
    2.83
     Lot
    2.58
     lots
    2.51
    lot
    2.49
     Lots
    2.38
    Lots
    2.16
    Lot
    2.14
    LOT
    2.09
    lots
    2.07
    Activations Density 0.252%

    No Known Activations