© 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. 3144
    Prev
    Next
    INDEX
    Explanations

    Listen without judgment

    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
    definite
    2.37
    eyn
    2.31
    ILLA
    2.24
    eh
    2.16
    rachten
    2.15
    ei
    2.14
     bolo
    2.12
    𝗧
    2.09
    𝖗
    2.08
    ografía
    2.07
    POSITIVE LOGITS
    coln
    3.41
    н
    3.35
    р
    2.78
    的版本
    2.62
     Divided
    2.58
    ırs
    2.58
     Endocrinol
    2.54
    の
    2.53
    కోవడం
    2.53
     Crystallogr
    2.51
    Activations Density 0.035%

    No Known Activations