© 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. 243300
    Prev
    Next
    INDEX
    Explanations

    to get

    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
     مشاهده
    0.47
     svog
    0.47
     ಅದರ
    0.47
     njegov
    0.46
    łej
    0.45
    ż
    0.44
     Kurt
    0.43
    łoży
    0.43
    сынын
    0.43
    ന്റ
    0.42
    POSITIVE LOGITS
    i
    0.50
     எத்தனை
    0.49
    יי
    0.48
    oppos
    0.46
    atibus
    0.44
    떼
    0.44
    that
    0.42
    essive
    0.42
    array
    0.42
    веря
    0.42
    Activations Density 0.000%

    No Known Activations