© 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. 67492
    Prev
    Next
    INDEX
    Explanations

    doubled; doubling; filling

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

    linked, associated, limitations, often

    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
    all
    0.59
    Luther
    0.51
     variations
    0.50
     Dependent
    0.48
    Petit
    0.47
    Dependent
    0.47
    は
    0.46
     Petit
    0.45
     alternatif
    0.44
    ᱽ
    0.44
    POSITIVE LOGITS
     நடிப்ப
    0.53
    페이지
    0.50
     pala
    0.46
     Kxa
    0.46
     прось
    0.45
    muc
    0.43
     گری
    0.42
     Atty
    0.42
    능
    0.41
    mazing
    0.41
    Activations Density 0.001%

    No Known Activations