© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 4888
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and fractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yní
    0.97
    arrerol
    0.95
    ického
    0.91
    ቑ
    0.85
    ódulo
    0.83
    embangunan
    0.82
    ల
    0.81
    ራሉ
    0.81
    ávat
    0.81
    derdag
    0.80
    POSITIVE LOGITS
     esoteric
    0.90
     prescriptive
    0.90
     hipster
    0.87
     anarch
    0.87
     humanist
    0.86
     innovative
    0.86
     eclectic
    0.86
     granular
    0.86
     LEGO
    0.84
     aristocratic
    0.84
    Activations Density 0.308%

    No Known Activations