© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 31503
    Prev
    Next
    INDEX
    Explanations

    multi-lingual content

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

    Privacy and compromising

    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_31_width_262k_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
    dependence
    0.45
    an
    0.44
    Ext
    0.44
     addictions
    0.44
    饗
    0.43
    ing
    0.42
     impeachment
    0.42
    }{$
    0.41
     augmentation
    0.41
    ass
    0.40
    POSITIVE LOGITS
    ementara
    0.59
     पोषक
    0.57
     раствора
    0.56
     തയ്യാ
    0.53
     раствор
    0.53
     був
    0.52
     препарат
    0.51
     بکر
    0.51
    糇
    0.51
    𒌦
    0.51
    Activations Density 0.000%

    No Known Activations