© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 202950
    Prev
    Next
    INDEX
    Explanations

    check before actions

    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
    ر
    0.53
     th
    0.51
     students
    0.50
     tutors
    0.48
     theses
    0.46
     glBindTexture
    0.46
     次
    0.46
    ちなみに
    0.45
    ちら
    0.45
     ဟ
    0.45
    POSITIVE LOGITS
    годно
    0.44
    instit
    0.42
    mington
    0.42
    optimal
    0.41
    imi
    0.40
    hemi
    0.40
     procesos
    0.40
     impeded
    0.40
    undum
    0.39
    onomi
    0.39
    Activations Density 0.006%

    No Known Activations