© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32988
    Prev
    Next
    INDEX
    Explanations

    phrases starting with pronouns or verbs

    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_22/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
    による
    -1.16
    つまり
    -1.16
     sätt
    -1.12
     :
    -1.08
     actually
    -1.07
     And
    -1.06
     did
    -1.05
     )
    -1.05
     except
    -1.05
    L
    -1.05
    POSITIVE LOGITS
    ⢓
    1.37
    Ꮂ
    1.34
    
    1.34
    橚
    1.30
    ⚢
    1.26
    вгений
    1.24
     chargé
    1.23
    opportunity
    1.21
    ܳ
    1.20
    姈
    1.20
    Activations Density 0.002%

    No Known Activations