© 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-262K
    4. 5080
    Prev
    Next
    INDEX
    Explanations

    security credentials, SSH, VPN, gpg

    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
    ઓ
    1.63
    \}$,
    1.59
    )$$
    1.59
    دى
    1.51
    $("
    1.49
    ઓની
    1.48
    \;
    1.46
    ...*/
    1.45
    ία
    1.45
    ,“
    1.45
    POSITIVE LOGITS
     kimia
    1.68
    𝗚
    1.61
     cepat
    1.57
    Minimize
    1.47
    𝗩
    1.47
     sei
    1.46
    𝗗
    1.46
    𝗟
    1.44
     falsa
    1.41
     Loved
    1.40
    Activations Density 0.085%

    No Known Activations