© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12375
    Prev
    Next
    INDEX
    Explanations

    Paid ads and promotions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     الز
    0.42
    secure
    0.42
    Secure
    0.41
     $\
    0.41
     software
    0.40
    MW
    0.40
    Proxy
    0.39
    体
    0.39
     temer
    0.39
     ${
    0.39
    POSITIVE LOGITS
    ເ
    0.51
    Ნ
    0.47
    ៖
    0.47
    larım
    0.47
    ້
    0.46
    ຣ
    0.45
    țională
    0.45
     ionized
    0.44
    oureux
    0.44
    Clic
    0.44
    Activations Density 0.000%

    No Known Activations