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. 46989
    Prev
    Next
    INDEX
    Explanations

    completely different

    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
     što
    1.10
    swagen
    1.09
    merksam
    1.08
    驗
    1.08
     prostu
    1.07
    स्वरूप
    1.06
    printf
    1.05
     uwagę
    1.04
    सम्
    1.03
    Verlag
    1.03
    POSITIVE LOGITS
     poderes
    1.24
    icier
    1.19
     divina
    1.19
     estad
    1.15
     Peachtree
    1.09
     merece
    1.08
    廂
    1.07
     ofertas
    1.06
     FIR
    1.05
     latest
    1.05
    Activations Density 0.001%

    No Known Activations