© 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. 131415
    Prev
    Next
    INDEX
    Explanations

    file types, events, descriptive words

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

    control and access

    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
    प्ति
    0.46
    щер
    0.45
    ர்ஸ்
    0.44
    脍
    0.44
    ellan
    0.44
    னோ
    0.44
    িলা
    0.43
     मेन
    0.43
    知的
    0.43
     टैंक
    0.43
    POSITIVE LOGITS
    Ꮩ
    0.40
     સામે
    0.39
    ピッ
    0.39
     quar
    0.39
     идут
    0.38
    自由
    0.37
     ➤
    0.37
     Etappe
    0.37
     sculpted
    0.37
     stairway
    0.37
    Activations Density 0.000%

    No Known Activations