© 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. 169391
    Prev
    Next
    INDEX
    Explanations

    underlying medical issue

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

    way something is

    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
     comod
    0.44
     dwelling
    0.44
    ၈
    0.43
     procédés
    0.43
    ْ
    0.43
    Participant
    0.43
     capitale
    0.42
    Bibliographie
    0.42
    rophot
    0.41
    ٠
    0.41
    POSITIVE LOGITS
    ic
    0.58
     advise
    0.55
    itan
    0.54
    wart
    0.51
     धारण
    0.51
     अहंकार
    0.50
    foil
    0.49
     развивается
    0.49
    ues
    0.49
    </strong>
    0.48
    Activations Density 0.001%

    No Known Activations