© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 936
    Prev
    Next
    INDEX
    Explanations

    verbs and adverbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "});
    1.04
     ihe
    1.04
    )\}$
    1.02
    :
    1.01
     the
    1.00
    }));
    0.97
     The
    0.96
    ")}
    0.96
    )$$
    0.94
     a
    0.93
    POSITIVE LOGITS
    지
    1.29
    ти
    1.23
    적인
    1.06
     zwią
    1.06
    на
    1.05
     precisamos
    1.02
    ੱਕ
    1.01
     იქნება
    1.01
    к
    1.00
     possiamo
    0.99
    Activations Density 0.000%

    No Known Activations