© 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-16K
    7. 12793
    Prev
    Next
    INDEX
    Explanations

    natural gas and cannabis strains

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

    multilingual content policy

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

    period

    np_max-act-logits · claude-4-5-sonnetTriggered by @sk5695
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_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
    それが
    0.54
    这也是
    0.48
    StartPreview
    0.43
     अर्थात्
    0.43
     ஃ
    0.42
    Ს
    0.42
    encher
    0.41
     しかし
    0.41
     लेख
    0.40
     หรือ
    0.40
    POSITIVE LOGITS
     and
    0.44
    órm
    0.42
     cuarta
    0.40
    ABASE
    0.39
     Rhonda
    0.39
     graham
    0.38
    ’
    0.38
     và
    0.37
     cál
    0.36
    했고
    0.36
    Activations Density 0.323%

    No Known Activations