© 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. 145394
    Prev
    Next
    INDEX
    Explanations

    hemorrhoids or adenoids

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

    anal and genital health issues

    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
     pedibusque
    0.50
    indungi
    0.48
    ニ
    0.46
     disponibilité
    0.46
     capacidade
    0.45
     Unido
    0.45
    DETA
    0.45
     এটির
    0.45
     ferrugineux
    0.44
    Segundo
    0.44
    POSITIVE LOGITS
    "
    0.41
     Fun
    0.41
     front
    0.41
     rocks
    0.41
     Flick
    0.40
     overstated
    0.40
     सहस्त्र
    0.40
     Flip
    0.39
     overrated
    0.39
     Melting
    0.38
    Activations Density 0.001%

    No Known Activations