© 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. 138392
    Prev
    Next
    INDEX
    Explanations

    safety and fragmentation attacks

    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
    DEFAULT
    0.53
     treba
    0.52
     diagnóstico
    0.51
     tratamiento
    0.49
    ﻯ
    0.49
    ÇÃO
    0.49
     adicional
    0.49
    לות
    0.48
     treble
    0.47
    ÇÕES
    0.47
    POSITIVE LOGITS
    <<"
    0.46
    k
    0.45
    atu
    0.43
    int
    0.43
    ik
    0.43
    picture
    0.42
    袬
    0.42
    ।
    0.41
    mt
    0.41
     মিস
    0.41
    Activations Density 0.000%

    No Known Activations