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-3-1B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 2547
    Prev
    Next
    INDEX
    Explanations

    generally still developing

    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_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
     annually
    0.63
    ulkar
    0.63
    रील
    0.62
     טור
    0.62
    onia
    0.61
     tain
    0.60
     बनवा
    0.59
    년
    0.59
     vind
    0.58
    媲
    0.58
    POSITIVE LOGITS
    Generally
    0.84
    generally
    0.76
     যতটুকু
    0.74
     Generally
    0.71
     anatomic
    0.71
    Absorption
    0.70
     कुल
    0.69
     OTHERWISE
    0.68
     generally
    0.68
     relativamente
    0.67
    Activations Density 0.210%

    No Known Activations