© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 48978
    Prev
    Next
    INDEX
    Explanations

    BC followed by letters or numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     livres
    0.43
     deixando
    0.42
    肚
    0.42
     contatto
    0.40
     grasa
    0.39
     permas
    0.39
     leaving
    0.39
    ">—
    0.39
     fatt
    0.38
     laissant
    0.38
    POSITIVE LOGITS
     BC
    0.54
    BC
    0.49
     Bc
    0.46
    bc
    0.43
     BCR
    0.42
     Bxc
    0.40
     Rich
    0.39
     BCG
    0.38
     Pov
    0.38
     Higher
    0.38
    Activations Density 0.011%

    No Known Activations