© 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. 11647
    Prev
    Next
    INDEX
    Explanations

    temperature ranges

    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
    <0x16>
    1.38
    льд
    1.36
     Joy
    1.26
     wept
    1.26
    <0x11>
    1.26
     tongue
    1.25
     laughs
    1.24
     दिखी
    1.24
     eight
    1.24
     jumpsuit
    1.23
    POSITIVE LOGITS
    iging
    1.07
    endering
    1.01
    awing
    0.96
    ingin
    0.94
    攻
    0.93
     prospecting
    0.92
    unding
    0.91
    okin
    0.90
     commun
    0.90
    ing
    0.89
    Activations Density 0.079%

    No Known Activations