© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 63867
    Prev
    Next
    INDEX
    Explanations

    medical symptoms, CSA, dissertation, lost

    np_acts-logits-general · gemini-2.5-flash-lite

    foreign scripts or languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cures
    0.47
     pessimism
    0.46
    ्रोत
    0.45
    簟
    0.45
     advices
    0.44
     surpluses
    0.43
    ренного
    0.43
     öl
    0.43
    繇
    0.43
     ideias
    0.42
    POSITIVE LOGITS
     אר
    0.52
    ар
    0.46
    ו
    0.45
     гла
    0.43
     كل
    0.43
    ẹp
    0.42
    Ду
    0.42
     ви
    0.42
    Eastern
    0.42
    נ
    0.42
    Activations Density 0.000%

    No Known Activations