© 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. 110635
    Prev
    Next
    INDEX
    Explanations

    random number generation, YAML, mixed, download

    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
     выпуск
    0.44
    漏
    0.42
    卒業
    0.40
     επο
    0.40
    毕业
    0.40
    畢業
    0.40
     escolar
    0.40
     움직
    0.40
     тек
    0.38
    γι
    0.38
    POSITIVE LOGITS
     दोनों
    0.50
    有两种
    0.50
     beiden
    0.50
     دونوں
    0.48
    दोनों
    0.47
    endrá
    0.47
    ongono
    0.47
    Ḥ
    0.46
     Größe
    0.46
     Beads
    0.46
    Activations Density 0.008%

    No Known Activations