© 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. 86636
    Prev
    Next
    INDEX
    Explanations

    selecting and managing security information

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

    specific types of

    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
     temporada
    0.47
    switching
    0.47
    jä
    0.46
    ﺀ
    0.46
     تصوی
    0.46
    しなければ
    0.45
    ffineTransform
    0.45
     WEATHER
    0.43
    fonction
    0.43
     schrift
    0.43
    POSITIVE LOGITS
    作业
    0.45
     Cars
    0.42
    నీ
    0.42
    akul
    0.42
     ít
    0.41
    从未
    0.40
    форм
    0.40
     }^{+}$
    0.39
    మ్యాచ్
    0.39
    ல்
    0.39
    Activations Density 0.000%

    No Known Activations