© 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. 155863
    Prev
    Next
    INDEX
    Explanations

    common words followed by specific words

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

    scientific discovery

    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
    igraf
    0.50
    om
    0.47
    我们就
    0.47
    ost
    0.46
     우리가
    0.46
     beginnetje
    0.46
    _'.$
    0.45
    入場
    0.45
    akur
    0.45
     कोटी
    0.45
    POSITIVE LOGITS
    বিট
    0.49
     Bertram
    0.46
    יא
    0.45
     incluyen
    0.43
    ୨
    0.43
     Judgment
    0.43
     incluye
    0.43
    Judgment
    0.41
    нит
    0.40
     răz
    0.40
    Activations Density 0.000%

    No Known Activations