© 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. 31-GEMMASCOPE-2-RES-262K
    7. 226791
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
    Human
    0.58
    Access
    0.54
    0
    0.54
    Organ
    0.50
    G
    0.48
    Indeed
    0.48
    Fluid
    0.48
    human
    0.48
    Call
    0.47
    Ten
    0.47
    POSITIVE LOGITS
     dormitory
    0.46
     rusk
    0.45
     onderwerp
    0.44
     পশ্চিম
    0.44
     comércio
    0.44
     abortions
    0.43
     algodón
    0.43
     inflación
    0.43
     fó
    0.43
    廬
    0.43
    Activations Density 0.004%

    No Known Activations