Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-65K
    4. 47422
    Prev
    Next
    INDEX
    Explanations

    Epoch and record identifiers

    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_65k_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
    struck
    1.12
     panning
    1.11
    CI
    1.06
    posit
    1.05
    noh
    1.04
    𝖗
    1.04
    AT
    1.03
    changing
    1.03
    l
    1.02
    ल
    1.02
    POSITIVE LOGITS
     cargas
    1.34
     svou
    1.29
     survivor
    1.27
     dites
    1.24
    ामुळे
    1.20
     muncul
    1.20
     Muitos
    1.19
     comienza
    1.18
     mì
    1.16
     necks
    1.16
    Activations Density 0.003%

    No Known Activations