© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 138030
    Prev
    Next
    INDEX
    Explanations

    instructions or explanations

    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
    tab
    0.46
     FISA
    0.44
    stride
    0.42
     τρό
    0.42
    š
    0.42
     bound
    0.42
    getLogger
    0.41
    table
    0.41
     tab
    0.41
     ratione
    0.41
    POSITIVE LOGITS
     invito
    0.49
    ле
    0.47
     রাসেল
    0.46
    Plant
    0.46
    景
    0.46
    耐
    0.45
     PLANTS
    0.45
    ఞ
    0.45
    衹
    0.45
     Solic
    0.44
    Activations Density 0.009%

    No Known Activations