© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 143747
    Prev
    Next
    INDEX
    Explanations

    affectionate address

    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_16_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
    D
    0.56
    of
    0.54
    ک
    0.52
    专业
    0.52
    一条
    0.51
    confident
    0.51
    有
    0.50
    ai
    0.49
    affect
    0.49
    R
    0.47
    POSITIVE LOGITS
     emuls
    0.49
     DJs
    0.48
     kaleidos
    0.47
     flore
    0.44
     Woh
    0.44
    ιάς
    0.44
     philosophers
    0.44
    KeyValuePair
    0.44
     přek
    0.43
     juries
    0.43
    Activations Density 0.000%

    No Known Activations