© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7806
    Prev
    Next
    INDEX
    Explanations

    setting conditions and origins

    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
     takže
    0.51
     tellement
    0.46
    ari
    0.44
     가서
    0.44
    とにかく
    0.42
    pleClass
    0.42
     ότι
    0.42
    :
    0.42
    ी
    0.41
    eduanya
    0.41
    POSITIVE LOGITS
     admittedly
    0.46
     despite
    0.37
    albeit
    0.36
     albeit
    0.35
    过了
    0.34
     কিনা
    0.34
     insbesondere
    0.34
     threatened
    0.33
     unsurprisingly
    0.33
     benchmark
    0.32
    Activations Density 0.166%

    No Known Activations