Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 5939
    Prev
    Next
    INDEX
    Explanations

    lounge access

    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_16_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
    k
    1.21
    ne
    1.14
    b
    1.02
    r
    0.99
    It
    0.98
    ll
    0.94
    da
    0.94
    st
    0.93
    j
    0.93
     on
    0.92
    POSITIVE LOGITS
     lounges
    1.31
     lounging
    1.19
     lounge
    1.07
    ździer
    1.04
    ка
    1.00
     reprises
    0.98
    刄
    0.96
    ви
    0.95
    ای
    0.95
    एमएस
    0.94
    Activations Density 0.000%

    No Known Activations