© 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. 16-GEMMASCOPE-2-RES-262K
    7. 28194
    Prev
    Next
    INDEX
    Explanations

    what it takes to

    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
    0.71
     جوړونک
    0.68
    CHILD
    0.67
    ્સ
    0.66
    <0xBE>
    0.66
     erweit
    0.66
    🤰
    0.65
     பெரும்பாலான
    0.64
    atorul
    0.64
     椅
    0.63
    POSITIVE LOGITS
    al
    0.92
    to
    0.87
    man
    0.71
     of
    0.69
    一
    0.68
    i
    0.68
     to
    0.68
    、
    0.65
    ,
    0.65
     for
    0.64
    Activations Density 0.008%

    No Known Activations