© 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. 206285
    Prev
    Next
    INDEX
    Explanations

    foreign characters and punctuation

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

    genetic factors and technology

    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
    Notes
    0.45
    BX
    0.43
    timestamps
    0.42
     теркә
    0.42
    候选
    0.42
    
    0.41
    繇
    0.41
    «.
    0.41
    dicts
    0.41
    书中
    0.41
    POSITIVE LOGITS
    ូ
    0.45
    ！？
    0.45
     അവിടെ
    0.44
     dre
    0.43
     agonizing
    0.43
    偶然
    0.42
     今年
    0.41
     Sadly
    0.41
     excruciating
    0.41
    🌩
    0.40
    Activations Density 0.000%

    No Known Activations