© 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. 9-GEMMASCOPE-2-RES-262K
    7. 9475
    Prev
    Next
    INDEX
    Explanations

    lists, pros, cons

    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_9_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
    ো
    0.99
     Gegensatz
    0.88
     Originally
    0.87
    на
    0.86
    k
    0.84
    м
    0.83
    이
    0.82
    ో
    0.80
    다른
    0.79
    ം
    0.79
    POSITIVE LOGITS
     weapons
    0.74
     some
    0.62
     the
    0.62
    ability
    0.61
     forecasting
    0.60
     apps
    0.59
     their
    0.58
     rural
    0.57
     misinformation
    0.57
     et
    0.57
    Activations Density 0.914%

    No Known Activations