© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 18719
    Prev
    Next
    INDEX
    Explanations

    building native applications

    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
     INSTALL
    0.89
    ]}/
    0.86
     Delegates
    0.82
     작성
    0.82
     promulg
    0.81
    JLabel
    0.81
     installers
    0.81
     crustaceans
    0.80
    PageRoute
    0.79
     জ্ঞানী
    0.79
    POSITIVE LOGITS
     लौट
    0.70
    लिये
    0.69
    ்
    0.67
     समान
    0.64
     vertical
    0.64
    Vertical
    0.63
    Peripheral
    0.63
    Single
    0.62
     Single
    0.61
     Peripheral
    0.59
    Activations Density 0.004%

    No Known Activations