© 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. 121571
    Prev
    Next
    INDEX
    Explanations

    safeguard the

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

    Search material overall

    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
     zodiac
    0.42
     confessions
    0.40
     instruct
    0.40
     prognostic
    0.40
     agh
    0.40
     enacting
    0.39
    电信
    0.39
    }}{|
    0.39
     Fav
    0.39
     confession
    0.39
    POSITIVE LOGITS
    Pada
    0.57
    rification
    0.55
    Setelah
    0.55
    пуляр
    0.54
    Sebagai
    0.54
     Sebagai
    0.54
     स्टाइलिश
    0.53
    hipping
    0.53
    ut
    0.51
    Jf
    0.51
    Activations Density 0.001%

    No Known Activations