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

    Neuronpedia

    Jacobian LensNEW
    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. 10038
    Prev
    Next
    INDEX
    Explanations

    reserve for future use

    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
     myeloma
    2.86
     contingency
    2.70
     fared
    2.68
     recognizable
    2.61
     omission
    2.57
    󠁢
    2.57
     decently
    2.56
    я
    2.56
    les
    2.56
    ına
    2.55
    POSITIVE LOGITS
    y
    3.74
    на
    3.68
    ০০
    2.92
    ০১
    2.91
    kjav
    2.76
    میں
    2.75
    ০
    2.73
    h
    2.73
     esclare
    2.71
    oirs
    2.70
    Activations Density 0.013%

    No Known Activations