© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 220274
    Prev
    Next
    INDEX
    Explanations

    Queen Elizabeth at

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

    comparing something to pre-training

    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_31_width_262k_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
    ]))
    0.47
    dice
    0.45
    D
    0.45
    InnoDB
    0.43
    location
    0.43
    magic
    0.43
    ূর্ন
    0.42
    ">*
    0.42
    name
    0.41
    fly
    0.41
    POSITIVE LOGITS
     NI
    0.54
     Ordnance
    0.49
     Mould
    0.48
     粉
    0.48
     เหมือน
    0.47
     PowerPoint
    0.46
     เหมาะ
    0.46
     Metal
    0.45
     Recruitment
    0.45
     Shams
    0.45
    Activations Density 0.000%

    No Known Activations