© 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. 43016
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases

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

    consent, safety, intimacy, and boundaries

    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
     pools
    0.44
     Pools
    0.43
     creates
    0.43
     in
    0.43
    ..
    0.42
    </strong>
    0.42
     rarely
    0.41
    :
    0.41
     http
    0.41
     Create
    0.41
    POSITIVE LOGITS
    ⴻ
    0.54
    ഭ്യാസ
    0.51
    提到的
    0.50
    结局
    0.49
     упомина
    0.49
     பருவ
    0.49
     엄청
    0.48
     但是
    0.48
    いましたが
    0.47
     intermédiaire
    0.47
    Activations Density 0.000%

    No Known Activations