© 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. 76813
    Prev
    Next
    INDEX
    Explanations

    not listed or allowed

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

    avoid robotic phrasing

    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
     powodu
    0.45
    :“
    0.44
     对象
    0.42
    الغ
    0.41
    :@
    0.40
     kunde
    0.40
     zb
    0.39
    荨
    0.39
     lading
    0.39
     Arts
    0.39
    POSITIVE LOGITS
     यूरोप
    0.47
     दशमलव
    0.47
     डाउनलोड
    0.46
    歐洲
    0.45
     असाल
    0.44
     Европе
    0.43
    accessible
    0.43
     मार्क
    0.43
    ጠቀ
    0.42
    вшись
    0.42
    Activations Density 0.000%

    No Known Activations