© 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. 67762
    Prev
    Next
    INDEX
    Explanations

    your + descriptive word

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

    romantic relationship silencing

    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
     inescap
    0.49
    ensical
    0.45
    ariate
    0.44
    陘
    0.44
    rocin
    0.43
    amentul
    0.43
     iure
    0.43
    anniksi
    0.43
    Հ
    0.42
     MHC
    0.42
    POSITIVE LOGITS
    ược
    0.56
    ])
    0.48
     shielding
    0.47
     scooped
    0.44
     milking
    0.42
     tripped
    0.42
     mined
    0.41
     bowled
    0.41
     গুঁ
    0.41
    ں
    0.41
    Activations Density 0.000%

    No Known Activations