© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3542
    Prev
    Next
    INDEX
    Explanations

    Gold, pink, cute, water, temperature

    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
    用户的
    0.40
     અથવા
    0.39
    两次
    0.39
    ṑ
    0.39
    প্রে
    0.38
    meier
    0.38
    markt
    0.38
    ǎi
    0.38
    뒹
    0.38
    ätten
    0.38
    POSITIVE LOGITS
     tpr
    0.49
     SGS
    0.48
     lcd
    0.46
     eps
    0.45
     cnc
    0.44
     Eph
    0.43
     EPR
    0.42
     smtp
    0.40
     tv
    0.40
     NCR
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.