© 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. 121054
    Prev
    Next
    INDEX
    Explanations

    for example

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

    privacy, security, databases, and appointments

    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
    ⇀
    0.50
    true
    0.49
    ᱔
    0.49
    EXPECT
    0.46
    ("./
    0.45
     ஆண்டுக
    0.45
    EPO
    0.44
    getContent
    0.44
    trending
    0.44
    旪
    0.44
    POSITIVE LOGITS
     Rupp
    0.45
    闲
    0.42
     szk
    0.41
     Frobenius
    0.40
     disseminate
    0.40
    կ
    0.40
     Vogel
    0.40
     duduk
    0.40
     spinach
    0.40
     mutta
    0.40
    Activations Density 0.000%

    No Known Activations