© 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-65K
    7. 177
    Prev
    Next
    INDEX
    Explanations

    numerical data

    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_65k_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
    Object
    0.27
    लंघन
    0.25
     forcément
    0.25
    otoxin
    0.24
    ׳
    0.24
    rün
    0.24
     obowią
    0.24
    کومت
    0.24
    ziehungs
    0.24
    ROBERT
    0.23
    POSITIVE LOGITS
    1
    0.41
    5
    0.38
    6
    0.38
    2
    0.37
    3
    0.36
     five
    0.34
     three
    0.34
     six
    0.34
    4
    0.32
     another
    0.31
    Activations Density 0.404%

    No Known Activations