© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 280
    Prev
    Next
    INDEX
    Explanations

    ending punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-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
     注
    1.52
    ويت
    1.49
    ‮
    1.42
     일반적으로
    1.41
    anesu
    1.40
     Brot
    1.40
     Gua
    1.37
    )]),
    1.37
     통한
    1.36
     معين
    1.36
    POSITIVE LOGITS
    !
    3.71
    ！
    2.98
    !"
    2.80
     !
    2.71
    !)
    2.64
    !!
    2.55
    !?
    2.46
    !”
    2.43
    ?!
    2.40
    !")
    2.40
    Activations Density 5.283%

    No Known Activations