© 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-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 5304
    Prev
    Next
    INDEX
    Explanations

    reasoning behind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
    ㄿ
    0.68
    新規
    0.68
    tolerance
    0.63
     граждан
    0.63
    Radar
    0.63
     mutual
    0.63
     Topic
    0.63
    ]^{+}$
    0.62
     例
    0.62
    Citizen
    0.62
    POSITIVE LOGITS
     behind
    2.80
     Behind
    2.51
    behind
    2.36
    Behind
    2.18
     derrière
    2.15
     detrás
    2.15
     achter
    1.79
     dietro
    1.77
     hinter
    1.61
     trás
    1.53
    Activations Density 0.339%

    No Known Activations