© 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. 186070
    Prev
    Next
    INDEX
    Explanations

    Semitic slur, pyramid schemes

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

    Japanese, English, German words

    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
    ⏱
    0.44
     promedio
    0.43
    तया
    0.43
    𝘄
    0.43
    ъем
    0.42
    🆙
    0.41
    Own
    0.40
    𝗢
    0.40
    𝘱
    0.40
    ικ
    0.39
    POSITIVE LOGITS
     全部
    0.51
     Aktivitäten
    0.48
     खु
    0.47
     NOTE
    0.46
    ”.
    0.46
     Shabbat
    0.45
     Tết
    0.45
     نوٹ
    0.45
     note
    0.45
    restrict
    0.44
    Activations Density 0.000%

    No Known Activations