© 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. 35698
    Prev
    Next
    INDEX
    Explanations

    what i mean

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

    various contexts

    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
     குற்றம்
    0.48
     చి
    0.48
    inz
    0.46
    epat
    0.46
    ekra
    0.46
     ambao
    0.45
    ᥱ
    0.45
     ब्रि
    0.45
     violate
    0.44
     ដែល
    0.44
    POSITIVE LOGITS
     Idani
    0.58
    ף
    0.55
    ل
    0.51
    지
    0.50
    핑
    0.47
    י
    0.47
    פה
    0.45
    办
    0.45
    দে
    0.45
    speedboat
    0.44
    Activations Density 0.000%

    No Known Activations