© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 396
    Prev
    Next
    INDEX
    Explanations

    contrast and conditionality

    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_16k_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
     hallmarks
    0.23
    <strong>
    0.22
    ⁢
    0.22
     şeklinde
    0.22
    R
    0.22
    G
    0.21
     ermöglichen
    0.21
    ​
    0.21
    ⁤
    0.21
    <b>
    0.20
    POSITIVE LOGITS
     మాత్రం
    0.35
     hingegen
    0.35
     नहीं
    0.32
    未必
    0.31
     δεν
    0.31
     certainly
    0.29
     dagegen
    0.29
    是没有
    0.29
     ਨਹੀਂ
    0.29
    就不会
    0.28
    Activations Density 6.055%

    No Known Activations