© 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. 35457
    Prev
    Next
    INDEX
    Explanations

    back ofstructure ofAt timesno liability

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

    code examples

    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
    Months
    0.49
    infested
    0.47
    MONTH
    0.47
    months
    0.47
    infected
    0.47
    مت
    0.46
    month
    0.46
    l
    0.45
    liy
    0.45
    jd
    0.44
    POSITIVE LOGITS
     Genomics
    0.52
     점점
    0.50
     Ayurved
    0.50
     Recorder
    0.49
     HCl
    0.49
    esco
    0.49
     Promoter
    0.48
     Molecular
    0.46
    器的
    0.46
    ོ་
    0.46
    Activations Density 0.000%

    No Known Activations