© 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. 31715
    Prev
    Next
    INDEX
    Explanations

    tragedy and survival

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

    categorizing by risk and effort

    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
    as
    0.59
     మరియు
    0.55
    0
    0.54
    いますが
    0.52
    your
    0.51
     மற்றும்
    0.50
    X
    0.49
    e
    0.49
    нт
    0.48
    AZ
    0.48
    POSITIVE LOGITS
     traumat
    0.63
     kematian
    0.61
     horrifying
    0.60
     horrible
    0.59
     frighten
    0.59
     terrifying
    0.58
     sobrevivir
    0.57
     बीमारी
    0.57
     কষ্ট
    0.56
     heartbreak
    0.56
    Activations Density 0.000%

    No Known Activations