© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 232793
    Prev
    Next
    INDEX
    Explanations

    describing "new" and "easy"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    న
    0.48
     впечат
    0.45
    จะเป็น
    0.44
    Escolhido
    0.44
    ៣
    0.44
    प्लिक
    0.43
    멤
    0.43
    ર્
    0.43
    Members
    0.43
     ediyorum
    0.42
    POSITIVE LOGITS
     not
    0.45
    这点
    0.40
    -
    0.39
     bagno
    0.39
     easily
    0.39
     Wu
    0.39
    ≤
    0.39
     farlo
    0.38
    簡単
    0.38
     Huang
    0.38
    Activations Density 0.000%

    No Known Activations