© 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. 22-GEMMASCOPE-2-RES-262K
    7. 14757
    Prev
    Next
    INDEX
    Explanations

    replace with

    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_22_width_262k_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
    Don
    0.66
    τητας
    0.64
    You
    0.63
     बस
    0.63
    』
    0.63
    Internal
    0.62
    Fem
    0.61
    》
    0.60
    还
    0.60
    ']."
    0.59
    POSITIVE LOGITS
     sebagai
    0.89
     together
    0.77
     volgens
    0.77
     sesuai
    0.76
     according
    0.75
    για
    0.75
     with
    0.75
     separately
    0.73
     dgn
    0.70
     alongside
    0.70
    Activations Density 0.033%

    No Known Activations