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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 8855
    Prev
    Next
    INDEX
    Explanations

    exam performance

    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
     mumkin
    0.59
    డియో
    0.59
    세요
    0.57
    やすい
    0.55
    کا
    0.55
    ﻒ
    0.55
     prelude
    0.54
    ה
    0.53
     predom
    0.53
    মেন্ট
    0.52
    POSITIVE LOGITS
    0
    0.82
    '],
    0.60
    ll
    0.58
    ny
    0.57
    O
    0.55
    icked
    0.55
    nt
    0.55
    ng
    0.55
    oll
    0.54
    icker
    0.53
    Activations Density 0.002%

    No Known Activations