© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 430
    Prev
    Next
    INDEX
    Explanations

    fast-paced variance accept

    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_16k_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
     aptly
    0.24
    ને
    0.22
     sultry
    0.22
     astrophys
    0.21
    :
    0.21
    tedir
    0.20
     бывшего
    0.20
    '...
    0.20
     unsettling
    0.20
     illustrious
    0.20
    POSITIVE LOGITS
    and
    0.29
    3
    0.26
     and
    0.26
    си
    0.24
     for
    0.23
    а
    0.22
    TV
    0.22
    with
    0.21
    у
    0.20
    िंग
    0.20
    Activations Density 6.055%

    No Known Activations