© 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. 44232
    Prev
    Next
    INDEX
    Explanations

    to get, to stay, to go, to access, to survive

    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
    н
    0.95
    р
    0.82
    д
    0.79
    л
    0.73
    ر
    0.72
    Дан
    0.71
    ግዳ
    0.70
    ン
    0.70
    к
    0.69
    ﻟ
    0.68
    POSITIVE LOGITS
    ek
    0.71
    aldi
    0.58
    kiewicz
    0.58
     Peers
    0.57
    鐲
    0.56
    ↵
    0.55
    keb
    0.55
    ATES
    0.54
     været
    0.54
    ون
    0.53
    Activations Density 0.002%

    No Known Activations