© 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. 219914
    Prev
    Next
    INDEX
    Explanations

    air conditioning and training requirements

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

    greeting phrases and positive adjectives

    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
     clustered
    0.49
     cluster
    0.48
     contaminated
    0.47
     clove
    0.47
     benzene
    0.47
     mile
    0.47
     custodian
    0.46
     corridor
    0.46
     unstructured
    0.46
    POSITIVE LOGITS
    مق
    0.61
    dbg
    0.49
    nbhd
    0.48
    িনবার্গ
    0.46
    bians
    0.46
    .>
    0.45
    编辑
    0.44
    ługa
    0.44
    eppo
    0.44
    tti
    0.43
    Activations Density 0.001%

    No Known Activations