© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 138731
    Prev
    Next
    INDEX
    Explanations

    no single, list using

    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
    تمد
    0.49
    question
    0.48
    l
    0.47
    it
    0.46
     gauge
    0.44
     Полу
    0.44
    и
    0.44
    step
    0.44
    ي
    0.44
    $\{
    0.43
    POSITIVE LOGITS
     prefque
    0.48
     morphologies
    0.45
     лише
    0.44
     inconvén
    0.43
     siglas
    0.43
     ainult
    0.42
     únicamente
    0.42
     ovviamente
    0.42
    FromThe
    0.42
     एजेंस
    0.42
    Activations Density 0.004%

    No Known Activations