© 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. 30338
    Prev
    Next
    INDEX
    Explanations

    our personal mission

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

    using System.Linq;

    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
     sillons
    0.49
     getUsers
    0.47
    ینی
    0.46
    ፍ
    0.45
     adultes
    0.44
     drifted
    0.44
    RequestBody
    0.44
    Yard
    0.43
    Requirement
    0.43
    হাম
    0.43
    POSITIVE LOGITS
     Осо
    0.47
    ia
    0.45
    kem
    0.43
     Та
    0.43
     масштаб
    0.43
     Documentary
    0.42
     Centrale
    0.42
     Tableau
    0.41
    📊
    0.41
    centric
    0.40
    Activations Density 0.000%

    No Known Activations