© 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. 117767
    Prev
    Next
    INDEX
    Explanations

    legal and business phrases

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

    suggestive content

    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
     condiv
    0.48
    自分で
    0.45
     condivid
    0.45
     зимо
    0.45
     alimentação
    0.44
     variabili
    0.44
    8
    0.44
    ܩ
    0.44
     теми
    0.44
     там
    0.43
    POSITIVE LOGITS
    ிற்
    0.42
    वीस
    0.42
     كلمه
    0.40
     massless
    0.40
     গুরুত্বপূর্ণ
    0.39
    یدم
    0.39
     मह
    0.39
    scriptions
    0.39
     Also
    0.38
    ुत
    0.38
    Activations Density 0.001%

    No Known Activations