© 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-65K
    7. 3992
    Prev
    Next
    INDEX
    Explanations

    because they

    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
    ordat
    0.96
     discontinuity
    0.93
     Marathon
    0.82
    到一个
    0.79
    तरी
    0.79
    慮
    0.77
    evi
    0.77
     Managers
    0.76
    惜
    0.76
    పం
    0.76
    POSITIVE LOGITS
     suffice
    2.33
     suffices
    2.18
     enough
    2.13
     suficient
    1.95
     достаточно
    1.93
     genug
    1.92
    enough
    1.91
     sufficient
    1.90
     cukup
    1.90
     genoeg
    1.82
    Activations Density 0.069%

    No Known Activations