© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 47802
    Prev
    Next
    INDEX
    Explanations

    time durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_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
    élix
    0.47
    tschaft
    0.46
    uteurs
    0.46
    ˢ
    0.44
     gesch
    0.43
    ût
    0.42
    ätten
    0.42
    elle
    0.42
     peint
    0.42
     soc
    0.41
    POSITIVE LOGITS
    ડિયા
    0.51
     ignoring
    0.48
     चुनावी
    0.48
     windy
    0.46
     केटी
    0.45
     can
    0.45
     commutative
    0.45
    𒊏
    0.44
     oceans
    0.44
     çerçe
    0.44
    Activations Density 0.000%

    No Known Activations