© 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-16K
    7. 5345
    Prev
    Next
    INDEX
    Explanations

    from, around, not, versa, fall

    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
     hoe
    1.25
    ﻰ
    1.10
     develop
    0.99
     এমনকি
    0.99
     однако
    0.98
    ."]
    0.98
    이라고
    0.97
    }"
    0.96
     Einen
    0.96
     uncover
    0.95
    POSITIVE LOGITS
    lated
    1.46
    lty
    1.45
    lah
    1.35
    ल
    1.35
    கிறது
    1.34
    CLUDES
    1.32
    liel
    1.32
    いる
    1.29
    lere
    1.29
    lui
    1.29
    Activations Density 0.083%

    No Known Activations