© 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
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5739
    Prev
    Next
    INDEX
    Explanations

    entertaining story or schedule meeting

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

    chill

    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_53_width_65k_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
    wireless
    0.39
    ሴ
    0.39
    蓄
    0.39
    vr
    0.38
    Final
    0.37
    fv
    0.37
     薄
    0.36
    vq
    0.36
    ](\
    0.35
    Parsed
    0.35
    POSITIVE LOGITS
     Chill
    0.81
     Chil
    0.80
     chill
    0.80
     chilling
    0.75
    Chill
    0.75
     chil
    0.75
     chilled
    0.73
    chill
    0.70
     chile
    0.64
     chilli
    0.64
    Activations Density 0.000%

    No Known Activations