© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 23535
    Prev
    Next
    INDEX
    Explanations

    scala code keywords: val, def, object

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
    ኪ
    0.39
    Compounds
    0.36
    capi
    0.36
    Succ
    0.35
     Compos
    0.35
    PRODUCTS
    0.34
    Instance
    0.34
     limitaciones
    0.34
    Zam
    0.33
    ǁ
    0.33
    POSITIVE LOGITS
     val
    0.71
    val
    0.63
    object
    0.57
    def
    0.53
     def
    0.53
     object
    0.53
     válvula
    0.52
     override
    0.51
     valves
    0.51
    override
    0.49
    Activations Density 0.002%

    No Known Activations