© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 41619
    Prev
    Next
    INDEX
    Explanations

    ```python import```

    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_262k_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
     bahawa
    1.41
     bahwa
    1.25
    mlung
    1.23
    ных
    1.20
     आवृ
    1.17
     அந்தக்
    1.17
    larda
    1.15
     ἀ
    1.15
     deple
    1.15
     inherent
    1.14
    POSITIVE LOGITS
    д
    1.41
    б
    1.38
    ce
    1.32
    ד
    1.30
    ер
    1.20
    де
    1.20
    يه
    1.16
    ו
    1.16
    ר
    1.16
    к
    1.13
    Activations Density 0.001%

    No Known Activations