© 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. 33099
    Prev
    Next
    INDEX
    Explanations

    measuring points and quantities

    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
     স্বাস্থ্য
    0.47
     ofici
    0.44
    ౖ
    0.42
    tembre
    0.42
     кеңсеси
    0.41
    ridged
    0.41
     వ్యక్
    0.41
    pflicht
    0.39
    ни
    0.39
    stic
    0.39
    POSITIVE LOGITS
     all
    0.49
     optimality
    0.48
     elimin
    0.46
    ෲ
    0.46
    ್ರಾ
    0.45
     myriad
    0.45
     euphoria
    0.44
     elim
    0.43
     emergence
    0.43
     coral
    0.42
    Activations Density 0.002%

    No Known Activations