© 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. 24605
    Prev
    Next
    INDEX
    Explanations

    punctuation or code separators

    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
     H
    0.49
    h
    0.47
     '
    0.47
    ke
    0.46
     씨
    0.43
     સ્ક
    0.42
     شماره
    0.41
    ก
    0.41
     çalışmaları
    0.40
     его
    0.40
    POSITIVE LOGITS
     ljud
    0.57
    fdPar
    0.57
    _
    0.55
    搾
    0.54
     koliko
    0.54
    𓐄
    0.53
    دود
    0.53
    glColor
    0.51
    􀂃
    0.51
    𒌨
    0.50
    Activations Density 0.001%

    No Known Activations