© 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. 17242
    Prev
    Next
    INDEX
    Explanations

    specific identifiers

    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
     života
    0.55
     Life
    0.48
     have
    0.48
     conseguir
    0.48
     descans
    0.47
     en
    0.46
    }\
    0.45
     espera
    0.45
     anastom
    0.45
     morir
    0.45
    POSITIVE LOGITS
    மிழ்
    0.48
     중심으로
    0.48
    issante
    0.47
    .${
    0.46
    欒
    0.46
    ফোন
    0.44
     راجس
    0.44
    orphisms
    0.44
     displaying
    0.43
    ፍተኛ
    0.43
    Activations Density 0.001%

    No Known Activations