© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 21173
    Prev
    Next
    INDEX
    Explanations

    affiliate links and referral codes

    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
    窥
    0.47
    ïdes
    0.42
    ்ப்பு
    0.41
     gaze
    0.40
     സമൂഹ
    0.40
     MPEG
    0.40
     gazing
    0.40
    ებისა
    0.40
    颐
    0.40
    स्तिष्क
    0.39
    POSITIVE LOGITS
    折扣
    0.58
    discount
    0.55
     referral
    0.55
     discount
    0.54
     promo
    0.52
    Discount
    0.52
     referrals
    0.52
     discounts
    0.51
     Discount
    0.51
     affiliate
    0.51
    Activations Density 0.027%

    No Known Activations