© 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. 99674
    Prev
    Next
    INDEX
    Explanations

    positive sentiment for experiences

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

    cors and your

    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
    ቨ
    0.54
    aecat
    0.51
     haloes
    0.48
    endswith
    0.48
    क्षिप्त
    0.47
    iobium
    0.45
    کروچ
    0.45
     arsine
    0.45
    ιστα
    0.44
    ວກ
    0.43
    POSITIVE LOGITS
    ur
    0.52
    res
    0.52
    :
    0.52
    ri
    0.50
    ac
    0.49
    is
    0.48
    len
    0.47
    ase
    0.47
     Ritter
    0.47
    ara
    0.46
    Activations Density 0.001%

    No Known Activations