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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118645
    Prev
    Next
    INDEX
    Explanations

    reciprocal, reciprocity, reciprocally, reciprocating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     bọn
    -0.77
    只想
    -0.68
     immu
    -0.67
    うる
    -0.66
    ⁙
    -0.66
    rainy
    -0.66
     pter
    -0.65
    までも
    -0.65
    ότε
    -0.65
    Gerard
    -0.64
    POSITIVE LOGITS
     reciprocal
    6.16
     Recipro
    5.31
     reciproc
    5.16
    reci
    5.13
     reciprocity
    5.03
     RECIP
    3.91
     recipro
    3.86
    RECIP
    3.22
    Rec
    3.13
     reci
    2.88
    Activations Density 0.118%

    No Known Activations