© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 94844
    Prev
    Next
    INDEX
    Explanations

    never looking, glad to, wants to

    np_acts-logits-general · gemini-2.5-flash-lite

    LangChain, CLIP, S3, Role, Platforms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    น
    0.47
    ιο
    0.46
    Performing
    0.46
     Performing
    0.44
    اه
    0.43
    ዓ
    0.41
    performing
    0.41
    颜值
    0.41
     protestors
    0.40
    瑪
    0.40
    POSITIVE LOGITS
     سوی
    0.50
     trx
    0.46
    ztal
    0.46
     frustrate
    0.45
     그대로
    0.44
    拦
    0.44
     publish
    0.42
     disconcert
    0.41
     पुजारी
    0.41
    lastKey
    0.41
    Activations Density 0.001%

    No Known Activations