© 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. 478
    Prev
    Next
    INDEX
    Explanations

    verb-adverb/preposition sequences

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

    verb + preposition/adverb

    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
     និង
    0.25
     这些
    0.25
     använda
    0.24
     কর্তৃক
    0.24
     الذين
    0.23
     tarafından
    0.23
    𝐲
    0.23
    }{\
    0.23
     आफ्नो
    0.23
     utilizzando
    0.22
    POSITIVE LOGITS
     culmin
    0.28
     bode
    0.26
     correspond
    0.24
    이드
    0.24
     coincide
    0.24
    Despatx
    0.24
     resonate
    0.23
     culminated
    0.23
     resemble
    0.23
     culminates
    0.23
    Activations Density 0.729%

    No Known Activations