© 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. 44691
    Prev
    Next
    INDEX
    Explanations

    risks and weaknesses

    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
     Constructors
    0.48
    ’
    0.44
    舜
    0.43
    |(
    0.42
     Holi
    0.42
    (|
    0.42
    .•
    0.41
     vuoden
    0.40
    ,|
    0.39
    ,​
    0.38
    POSITIVE LOGITS
     precipitated
    0.50
     добы
    0.49
     उत्पादन
    0.49
     больше
    0.48
     непосред
    0.46
     upstream
    0.46
     давления
    0.46
    ties
    0.46
     peeling
    0.46
     данным
    0.45
    Activations Density 0.000%

    No Known Activations