© 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. 136693
    Prev
    Next
    INDEX
    Explanations

    secretly taken, seeking to, relationship with

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

    warm, tied up, choke, tongue

    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
     Patent
    0.52
     Technological
    0.48
     Crossing
    0.46
     Archaeological
    0.46
     計
    0.44
     mnoh
    0.44
     tecnológico
    0.44
     În
    0.43
     Plan
    0.43
    脣
    0.42
    POSITIVE LOGITS
    IMI
    0.50
    imi
    0.47
     אס
    0.46
    बाड़ी
    0.46
     renormal
    0.45
    (!$
    0.45
    Dirt
    0.44
    ständig
    0.44
    aundry
    0.44
    лович
    0.43
    Activations Density 0.000%

    No Known Activations