© 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. 48101
    Prev
    Next
    INDEX
    Explanations

    social media influencers and creators

    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
    ری
    0.71
    ید
    0.71
    ل
    0.69
    یی
    0.67
    لک
    0.67
    ک
    0.66
    نی
    0.65
     ኦ
    0.64
    .”)
    0.61
    K
    0.61
    POSITIVE LOGITS
    -
    0.98
    \
    0.85
    (
    0.69
    :
    0.65
    rive
    0.61
    ries
    0.60
    那就是
    0.60
    by
    0.59
     kom
    0.58
    carte
    0.58
    Activations Density 0.012%

    No Known Activations