© 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. 192098
    Prev
    Next
    INDEX
    Explanations

    availability, flexible, friend, lunches

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

    down in, tower suddenly

    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
    س
    0.54
     Sea
    0.51
    مس
    0.49
    Sea
    0.48
     offshore
    0.45
    סי
    0.44
    ص
    0.44
     marit
    0.43
     sea
    0.43
    ს
    0.43
    POSITIVE LOGITS
     трево
    0.49
     গভর্ন
    0.47
     horrifying
    0.47
    ধ্ব
    0.46
     ধ্বংস
    0.45
     লড়াই
    0.45
     தேர்தல்
    0.45
     борь
    0.45
     রাস্তায়
    0.44
    するには
    0.44
    Activations Density 0.000%

    No Known Activations