© 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. 162911
    Prev
    Next
    INDEX
    Explanations

    online experience or system

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

    virtual machine or simulated environment

    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
     সামান্য
    0.45
    wia
    0.44
     InputAction
    0.44
    тпу
    0.44
     obstruct
    0.43
     obstructing
    0.43
     dokład
    0.43
    ᱩ
    0.43
     partially
    0.43
    wość
    0.43
    POSITIVE LOGITS
    BRE
    0.51
    aaaa
    0.46
     رقم
    0.45
    垕
    0.45
     BRE
    0.44
    َرَ
    0.44
    飜
    0.44
    aa
    0.44
    畈
    0.44
    ேன்
    0.43
    Activations Density 0.003%

    No Known Activations