© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14744
    Prev
    Next
    INDEX
    Explanations

    age and life stages

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

    references to childhood or being young, including terms like "child", "children", "young", and "kid".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     unn
    -1.41
    报纸
    -1.37
     flamboyant
    -1.36
    
    -1.27
    ほとん
    -1.25
    蹀
    -1.24
     lauded
    -1.23
    買う
    -1.22
    
    -1.21
    饸
    -1.19
    POSITIVE LOGITS
     There
    1.27
     there
    1.26
     at
    1.20
     or
    1.20
     it
    1.17
     albo
    1.11
    There
    1.11
    holdings
    1.10
     ONLY
    1.09
     get
    1.07
    Activations Density 0.041%

    No Known Activations