© 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. 182598
    Prev
    Next
    INDEX
    Explanations

    specific word combinations or sequences

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

    emotions and states

    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
    キット
    0.44
     ktoś
    0.42
     darah
    0.42
     preparados
    0.40
    ]][
    0.40
     писать
    0.40
     educ
    0.40
    says
    0.40
     preparing
    0.39
     pangkat
    0.39
    POSITIVE LOGITS
     તેમની
    0.47
    aily
    0.45
    琬
    0.43
    ⌵
    0.43
    และความ
    0.43
     зре
    0.42
    萬元
    0.42
    ंदा
    0.41
    Edges
    0.41
     ધો
    0.41
    Activations Density 0.007%

    No Known Activations