© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 14882
    Prev
    Next
    INDEX
    Explanations

    product brand names and items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_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
     peroxidation
    1.06
     NGOs
    1.05
     PUBG
    1.04
     Minimalism
    1.01
     kaufen
    1.01
     KYC
    1.01
     Tiktok
    1.00
    买
    1.00
     MOQ
    0.97
     comprador
    0.97
    POSITIVE LOGITS
     Legacy
    0.76
    Star
    0.75
     Chrysler
    0.75
     Star
    0.74
    Abstract
    0.71
     Rac
    0.71
    Rac
    0.70
     Item
    0.69
    Ordinate
    0.69
     Dodge
    0.69
    Activations Density 0.030%

    No Known Activations