© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 8632
    Prev
    Next
    INDEX
    Explanations

    `its` or `itself` followed by a noun

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

    words ending in a “-y”/“-ty”/“-cy” suffix (i.e. the morphological noun/adjective endings you see in chocolatey, potency, society, etc.)

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     głównie
    -1.58
     two
    -1.43
    These
    -1.36
    alties
    -1.32
    Jegyzetek
    -1.32
    Estas
    -1.32
     with
    -1.30
    </h3>
    -1.28
    Cuándo
    -1.27
    When
    -1.27
    POSITIVE LOGITS
     its
    1.95
    它的
    1.45
    pineapple
    1.40
    ufc
    1.36
    					
    1.35
     itself
    1.34
     城市
    1.34
    </b>
    1.33
     苹果
    1.25
     hochzeit
    1.24
    Activations Density 0.156%

    No Known Activations