© 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. 31-GEMMASCOPE-2-RES-16K
    7. 3142
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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_31_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
     priest
    0.42
    xyplot
    0.40
    0.40
    ufth
    0.39
    }_{
    0.38
     undisclosed
    0.37
     nedenle
    0.37
    apanicolaou
    0.37
     endangered
    0.37
     presumably
    0.36
    POSITIVE LOGITS
    то
    0.52
    킹
    0.45
    인지
    0.45
    ти
    0.43
    т
    0.41
    рити
    0.41
    от
    0.41
    дин
    0.40
    נו
    0.40
    как
    0.40
    Activations Density 0.288%

    No Known Activations