© 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. 4355
    Prev
    Next
    INDEX
    Explanations

    movement through or from

    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
     svom
    0.38
    棪
    0.37
    し
    0.36
    эх
    0.36
     svůj
    0.35
     joli
    0.35
     cerca
    0.34
     ښ
    0.34
    曷
    0.34
     leaned
    0.34
    POSITIVE LOGITS
    from
    0.44
     from
    0.42
    มาจาก
    0.37
    through
    0.37
     statements
    0.36
    verbal
    0.35
     från
    0.34
     verbal
    0.34
     out
    0.34
     न्यू
    0.33
    Activations Density 0.142%

    No Known Activations