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. 1757
    Prev
    Next
    INDEX
    Explanations

    Several factors

    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
    L
    0.37
    P
    0.37
    D
    0.36
    Pago
    0.35
    own
    0.35
    Dense
    0.34
     or
    0.33
    V
    0.33
    Bomb
    0.32
    cancer
    0.32
    POSITIVE LOGITS
     factors
    0.62
     reasons
    0.57
     특징
    0.56
     downsides
    0.53
     Factors
    0.53
     characteristics
    0.53
     motivations
    0.51
     ویژگی
    0.50
     Gründe
    0.50
     факторы
    0.49
    Activations Density 2.878%

    No Known Activations