© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 3146
    Prev
    Next
    INDEX
    Explanations

    words ending in "ic", "le", "al" or "ore"

    np_acts-logits-general · gemini-2.5-flash-lite

    keybord or stand,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CheckException
    0.36
     TestAvg
    0.34
    㶪
    0.34
    cevam
    0.33
    㸸
    0.33
     BLUENRG
    0.33
     CharPtr
    0.31
     ReturnVal
    0.31
     previewBuilder
    0.31
     ObjData
    0.31
    POSITIVE LOGITS
     
    0.40
    i
    0.36
    -
    0.35
    r
    0.35
    le
    0.35
    l
    0.35
    ic
    0.33
    v
    0.33
    '
    0.32
    m
    0.32
    Activations Density 0.074%

    No Known Activations