© 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. 16-GEMMASCOPE-2-RES-262K
    7. 106154
    Prev
    Next
    INDEX
    Explanations

    northbound, southbound, eastbound

    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_16_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
    ostante
    0.66
    O
    0.64
    ש
    0.63
    og
    0.63
     جسے
    0.61
    laces
    0.59
    ່ານ
    0.59
    larda
    0.59
    lardan
    0.59
    そも
    0.59
    POSITIVE LOGITS
    i
    0.68
    م
    0.65
     It
    0.64
    ي
    0.61
    м
    0.59
    ม
    0.55
     mehreren
    0.55
    អ៊ី
    0.54
     questionnaires
    0.53
     Publisher
    0.53
    Activations Density 0.000%

    No Known Activations