© 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. 16619
    Prev
    Next
    INDEX
    Explanations

    nouns followed by prepositions or verbs

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

    business and work accomplishment

    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
     forment
    0.54
     wry
    0.54
     literally
    0.50
    緍
    0.47
    )--
    0.46
     �
    0.46
    }--
    0.46
     --
    0.45
     soooo
    0.45
     ½
    0.45
    POSITIVE LOGITS
     subpar
    0.69
    ًا
    0.57
    ᵉ
    0.54
     تقریباً
    0.52
     ​​
    0.51
     XNUMX
    0.50
     Shayari
    0.50
    𝕘
    0.49
    а
    0.48
     asimismo
    0.48
    Activations Density 0.047%

    No Known Activations