© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 114841
    Prev
    Next
    INDEX
    Explanations

    domain registrations, TLDs

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

    actions or states

    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
     salient
    0.44
    ച
    0.43
    Tai
    0.43
     thickness
    0.40
     vocês
    0.40
    Sar
    0.40
     ہ
    0.39
    タイ
    0.39
     знаходиться
    0.39
     içerisinde
    0.39
    POSITIVE LOGITS
    sns
    0.62
    '}
    0.57
     प्रकट
    0.54
    ')
    0.53
    ओएस
    0.51
     दलों
    0.49
    する必要があります
    0.49
    dx
    0.48
    㚣
    0.47
    snp
    0.47
    Activations Density 0.000%

    No Known Activations