© 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. 156330
    Prev
    Next
    INDEX
    Explanations

    specific nouns and contexts

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

    Earth, humans, cybersecurity, 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
    ູ
    0.49
    )+'
    0.46
    Exerc
    0.42
    V
    0.42
    舌
    0.42
     भाष
    0.42
    一种
    0.41
    第二百
    0.41
    N
    0.40
    ето
    0.40
    POSITIVE LOGITS
    knock
    0.49
     পুজ
    0.48
    zilla
    0.48
     weren
    0.47
    zawa
    0.47
     évolution
    0.46
     সিক
    0.46
     Precambrian
    0.46
     veya
    0.44
    chunks
    0.44
    Activations Density 0.002%

    No Known Activations