© 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. 13-GEMMASCOPE-2-RES-16K
    7. 14248
    Prev
    Next
    INDEX
    Explanations

    browning, thickening, scrambling

    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_13_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
     иногда
    1.06
     ankaŭ
    1.06
    ometimes
    0.96
    賃
    0.93
    Sometimes
    0.92
    Следу
    0.92
     quelquefois
    0.92
    ногда
    0.89
     нередко
    0.88
    ]}
    0.88
    POSITIVE LOGITS
     iniziamo
    1.54
     prelude
    1.53
     initial
    1.51
     zunächst
    1.47
     inital
    1.45
     comenzamos
    1.44
     inicial
    1.41
    initial
    1.40
     prelimin
    1.38
     precursor
    1.35
    Activations Density 0.146%

    No Known Activations