© 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. 5357
    Prev
    Next
    INDEX
    Explanations

    1 sentence

    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
    -
    0.24
    _
    0.22
    ,
    0.22
    :
    0.20
    er
    0.18
    j
    0.17
    '
    0.17
    ia
    0.16
    ’
    0.16
    ?
    0.16
    POSITIVE LOGITS
     womenProduct
    0.21
     pcMove
    0.18
    粎
    0.17
    𝚆
    0.17
     lLoginID
    0.17
     multiSelectList
    0.17
     Timatic
    0.17
    लट्
    0.17
     GoObject
    0.16
     splike
    0.16
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.