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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 53002
    Prev
    Next
    INDEX
    Explanations

    educational institutions and technical specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thermoplastics
    0.43
     boxe
    0.38
     xhrObj
    0.37
     sessions
    0.35
    (;
    0.35
     meshes
    0.35
     txtbtn
    0.34
     strat
    0.34
    జయ
    0.34
     září
    0.34
    POSITIVE LOGITS
    educated
    0.46
    кров
    0.43
    preferred
    0.41
    佩
    0.41
    ოს
    0.40
    willing
    0.40
    بلغ
    0.39
     பின்பற்ற
    0.39
    ور
    0.38
    živ
    0.38
    Activations Density 0.001%

    No Known Activations