© 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. 1005
    Prev
    Next
    INDEX
    Explanations

    BLENUS heat goals modifications

    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
     dissident
    1.37
     inwardly
    1.29
     permettant
    1.29
    当
    1.28
     nosso
    1.28
     nossos
    1.27
     mãe
    1.27
     nossas
    1.25
    ⓵
    1.24
     primeiro
    1.22
    POSITIVE LOGITS
    ल
    1.18
    매
    1.11
    ns
    0.96
    o
    0.94
    tariff
    0.94
    ness
    0.93
    mes
    0.93
    lade
    0.92
    nak
    0.92
    oises
    0.90
    Activations Density 0.000%

    No Known Activations