© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 92509
    Prev
    Next
    INDEX
    Explanations

    offers and apologies

    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_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
     substitution
    0.44
     crisis
    0.42
     plena
    0.42
     lounge
    0.42
    ﺮ
    0.42
     chemistry
    0.42
     recibieron
    0.41
     subsystem
    0.41
     cardiology
    0.41
     dislocation
    0.41
    POSITIVE LOGITS
    ጅ
    0.45
     acred
    0.42
     ఇ
    0.41
     க்
    0.40
     แถม
    0.40
     A
    0.40
     Ying
    0.39
    太平
    0.39
     Aws
    0.39
    缠
    0.38
    Activations Density 0.008%

    No Known Activations