© 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. 242258
    Prev
    Next
    INDEX
    Explanations

    legal and financial terms

    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
     position
    0.45
    is
    0.45
    ሎ
    0.43
     protagonists
    0.43
    u
    0.43
     city
    0.43
     talents
    0.41
     gulp
    0.40
     sort
    0.40
    Mor
    0.40
    POSITIVE LOGITS
     SIRT
    0.48
     मैती
    0.48
    akkhati
    0.46
    切割
    0.46
     Corolle
    0.46
    癤
    0.46
     PML
    0.45
     PKD
    0.45
    ઃ
    0.45
     UNIX
    0.44
    Activations Density 0.001%

    No Known Activations