© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 676
    Prev
    Next
    INDEX
    Explanations

    Gemma me

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
    上也
    0.67
     atual
    0.64
    िकोण
    0.64
    _
    0.64
     affaires
    0.63
     envie
    0.60
     able
    0.60
     conhecimentos
    0.57
     identify
    0.57
    Destination
    0.57
    POSITIVE LOGITS
     [§
    1.09
    ²,
    1.03
    、【
    0.99
    ®,
    0.94
    ³,
    0.93
     Styles
    0.89
    ,...,
    0.88
     Spectroscopy
    0.87
     עם
    0.86
     ಎಂದು
    0.86
    Activations Density 0.072%

    No Known Activations