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. 47680
    Prev
    Next
    INDEX
    Explanations

    Consumers are, People buy

    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
    вання
    1.15
    לע
    1.07
    cknowled
    1.05
    ר
    1.02
    üste
    0.99
    ৬০
    0.98
    ţă
    0.98
     moderate
    0.98
    רים
    0.97
    ции
    0.94
    POSITIVE LOGITS
    经营
    1.27
    此
    1.16
     negocio
    1.16
     soldado
    1.13
     atento
    1.12
     jugador
    1.10
     allons
    1.10
     此
    1.08
    的时间
    1.08
     tráfico
    1.08
    Activations Density 0.002%

    No Known Activations