© 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. 699
    Prev
    Next
    INDEX
    Explanations

    names and places

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

    Gemma team at Google DeepMind

    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
     Marie
    0.39
     Folk
    0.39
     Fold
    0.36
     Josiah
    0.36
     Titus
    0.36
     Eun
    0.35
    𝚍
    0.35
     Coke
    0.35
     Clover
    0.35
     Ngo
    0.35
    POSITIVE LOGITS
    jab
    0.47
    Jab
    0.44
    Rey
    0.43
     Jab
    0.40
    carb
    0.40
    Jas
    0.39
     jab
    0.38
    山本
    0.38
    雷
    0.37
    sab
    0.36
    Activations Density 0.048%

    No Known Activations