© 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
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 4113
    Prev
    Next
    INDEX
    Explanations

    social media

    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
     لکھنے
    0.62
    менение
    0.60
     ہُ
    0.57
     پھر
    0.56
    desIP
    0.56
    ﻤ
    0.56
    <unused76>
    0.54
     भने
    0.54
    ați
    0.54
    ਇ
    0.53
    POSITIVE LOGITS
    s
    1.27
    re
    1.12
    t
    1.10
    c
    0.93
    ش
    0.86
    to
    0.84
    h
    0.84
    </td>
    0.81
    w
    0.78
    </h3>
    0.77
    Activations Density 0.008%

    No Known Activations