© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3168
    Prev
    Next
    INDEX
    Explanations

    numbers and words

    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_65k_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
     one
    2.02
     both
    1.88
    蜊
    1.86
    脷
    1.85
     organisation
    1.82
    ouncement
    1.81
     rém
    1.71
    сро
    1.71
    Organisation
    1.69
     organisers
    1.66
    POSITIVE LOGITS
    7
    5.06
    8
    4.91
    6
    4.87
    5
    4.54
    0
    4.51
    9
    4.47
    4
    4.42
    3
    3.99
    º
    3.97
    ️⃣
    3.40
    Activations Density 0.451%

    No Known Activations