© 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. 100418
    Prev
    Next
    INDEX
    Explanations

    bilateral basis

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

    marketing communications

    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
     onderwerp
    0.53
    酴
    0.52
     செய்வத
    0.52
    贬
    0.51
     suht
    0.49
    Ტ
    0.48
    État
    0.48
    壃
    0.46
     состояния
    0.46
    䢀
    0.46
    POSITIVE LOGITS
     that
    0.61
    that
    0.56
    앙
    0.50
    mans
    0.48
    ibrate
    0.46
    <code>
    0.45
     তাহাতে
    0.44
    mama
    0.44
    bibnamefont
    0.43
    bf
    0.43
    Activations Density 0.001%

    No Known Activations