© 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. 13-GEMMASCOPE-2-RES-16K
    7. 4957
    Prev
    Next
    INDEX
    Explanations

    from crashing

    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_13_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
     Tales
    1.09
    ie
    1.09
    j
    1.09
    i
    1.08
    CB
    1.06
    le
    1.04
    lé
    1.04
    ctus
    1.01
    ్
    0.99
    ople
    0.98
    POSITIVE LOGITS
     れ
    1.08
     flexibility
    1.06
    弹性
    1.03
     strongly
    1.01
     toxicity
    0.99
     лига
    0.98
    AndKeys
    0.98
     ď
    0.97
     tightly
    0.97
    છા
    0.96
    Activations Density 0.018%

    No Known Activations