© 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. 86680
    Prev
    Next
    INDEX
    Explanations

    consulting firm, our needs

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

    infrastructure require Present must wonderfully

    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
    MASTER
    0.44
    も
    0.44
    ্বন
    0.43
    COMMAND
    0.43
    ⇢
    0.43
     Variability
    0.42
    äum
    0.42
    ੦
    0.42
    ↯
    0.42
    ()),
    0.42
    POSITIVE LOGITS
    لات
    0.51
    رر
    0.44
    f
    0.44
     annen
    0.42
    ภาค
    0.41
     &.
    0.41
     supportive
    0.41
    裝
    0.41
     ozbil
    0.40
     ileri
    0.40
    Activations Density 0.000%

    No Known Activations