© 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. 77495
    Prev
    Next
    INDEX
    Explanations

    basic understanding

    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
     accompanied
    0.46
     ===
    0.44
     aan
    0.44
    inthe
    0.43
     radiant
    0.43
     unassuming
    0.42
     manifested
    0.40
     unremarkable
    0.40
     gleaming
    0.40
     सिद्धार्थ
    0.40
    POSITIVE LOGITS
    谟
    0.46
    Mâc
    0.44
    andır
    0.43
    ባቸው
    0.41
     και
    0.41
    ufieurs
    0.41
    その他の
    0.41
    ős
    0.40
    焐
    0.39
    <0x91>
    0.38
    Activations Density 0.008%

    No Known Activations