© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 1337
    Prev
    Next
    INDEX
    Explanations

    months, especially today

    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_65k_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
    Convolution
    0.26
    Encoded
    0.25
    ScriptObject
    0.25
    Histogram
    0.24
    Descriptor
    0.24
     protéines
    0.24
    ihilation
    0.24
    鹄
    0.24
    Rigidbody
    0.24
     hyperplane
    0.24
    POSITIVE LOGITS
     November
    0.72
     October
    0.70
     April
    0.63
     February
    0.63
     January
    0.62
     December
    0.61
     June
    0.60
     September
    0.60
     July
    0.59
     March
    0.58
    Activations Density 0.170%

    No Known Activations