© 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. 6314
    Prev
    Next
    INDEX
    Explanations

    score or final value

    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
    پ
    0.59
     publiques
    0.58
    пти
    0.55
    Setelah
    0.52
    के
    0.51
    nous
    0.50
     públicos
    0.50
    ਨ
    0.49
    То
    0.49
    to
    0.48
    POSITIVE LOGITS
     thiệt
    0.50
    üedad
    0.44
     Synthesis
    0.43
    áme
    0.42
    Synthesis
    0.42
    ývá
    0.41
     Digests
    0.41
     giày
    0.41
     оста
    0.40
     офі
    0.40
    Activations Density 0.001%

    No Known Activations