© 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. 12265
    Prev
    Next
    INDEX
    Explanations

    entities and specific terms

    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
    琙
    1.54
    ስቃ
    1.51
    TabText
    1.48
    ሏ
    1.46
    <unused1203>
    1.46
    BEDATUM
    1.45
    alarına
    1.45
    𒐤
    1.45
     ৯ম
    1.45
    鿢
    1.44
    POSITIVE LOGITS
     Car
    1.20
     pan
    1.09
     car
    1.07
     de
    1.06
     CAR
    1.03
     Att
    1.03
     go
    1.03
    Car
    1.02
     Carol
    1.02
    onder
    1.02
    Activations Density 0.305%

    No Known Activations