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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 3596
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and conditions

    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_53_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
    nearest
    0.45
     precisely
    0.41
    entukan
    0.41
     Hence
    0.40
     (=
    0.40
     \<
    0.39
     किमान
    0.38
    requently
    0.38
    <unused59>
    0.38
    Nearest
    0.38
    POSITIVE LOGITS
     injustices
    0.74
     shenanigans
    0.73
     ideologies
    0.70
     intricacies
    0.69
     antics
    0.67
     stipulations
    0.67
     teachings
    0.65
     hardships
    0.65
     restraints
    0.65
     dealings
    0.64
    Activations Density 0.051%

    No Known Activations