© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6117
    Prev
    Next
    INDEX
    Explanations

    legal associations

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

    word followed by acronym component

    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
    蹇
    0.38
    ifaiFace
    0.37
    叄
    0.37
    AllCaps
    0.37
    𒉈
    0.37
     المصفوفه
    0.36
    す楽
    0.36
     Oath
    0.36
    𒈗
    0.36
    ječ
    0.35
    POSITIVE LOGITS
     DT
    3.56
    DT
    3.30
     GT
    3.14
     dt
    3.03
    dt
    2.97
     JT
    2.84
    GT
    2.81
    Dt
    2.80
     BT
    2.75
     VT
    2.72
    Activations Density 0.208%

    No Known Activations