© 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. 8309
    Prev
    Next
    INDEX
    Explanations

    sides and comparisons

    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
    JMenuItem
    0.95
    \}=\
    0.91
    複合
    0.84
    lnk
    0.84
     पत्र
    0.82
    фессиона
    0.82
    უფ
    0.81
    μού
    0.81
     مبت
    0.80
     απα
    0.79
    POSITIVE LOGITS
     side
    4.75
     Side
    4.22
    side
    4.16
    Side
    4.07
     sides
    3.99
     SIDE
    3.98
    SIDE
    3.41
    側
    3.40
     lado
    3.24
    sides
    3.23
    Activations Density 0.374%

    No Known Activations